CI, build & docker updates

rm makefile
basic test
add chaindata fixture
simplify publish workflow

.dockerignore

@@ -0,0 +1 @@
+.git

.gitea/workflows/publish.yml

@@ -0,0 +1,28 @@
+name: Publish Docker image
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  docker-build:
+    name: Run docker build
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - id: vars
+        name: Output SHA and version tag
+        run: |
+          echo "sha=${GITHUB_SHA:0:7}" >> $GITHUB_OUTPUT
+          echo "tag=${GITHUB_REF#refs/tags/}" >> $GITHUB_OUTPUT
+      - name: Build and tag image
+        run: |
+          docker build . \
+          -t cerc-io/eth-statediff-service \
+          -t git.vdb.to/cerc-io/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.sha}} \
+          -t git.vdb.to/cerc-io/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.tag}}
+      - name: Push image tags
+        run: |
+          echo ${{ secrets.GITEA_PUBLISH_TOKEN }} | docker login https://git.vdb.to -u cerccicd --password-stdin
+          docker push git.vdb.to/cerc-io/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.sha}}
+          docker push git.vdb.to/cerc-io/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.tag}}

.gitea/workflows/tests.yml

@@ -0,0 +1,65 @@
+name: Tests
+
+on:
+  pull_request:
+    branches: '*'
+  push:
+    branches:
+      - main
+      - ci-test
+  workflow_call:
+
+# Needed until we can incorporate docker startup into the executor container
+env:
+  DOCKER_HOST: unix:///var/run/dind.sock
+
+jobs:
+  integration-tests:
+    name: Run integration tests
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-go@v3
+        with:
+          go-version-file: go.mod
+          check-latest: true
+      - name: Run dockerd
+        run: |
+          dockerd -H $DOCKER_HOST --userland-proxy=false &
+          sleep 5
+      - name: Run DB container
+        run: docker compose -f test/compose.yml up --wait
+      - name: Configure Gitea access
+        env:
+          TOKEN: ${{ secrets.CICD_REPO_TOKEN }}
+        run: |
+          git config --global url."https://$TOKEN:@git.vdb.to/".insteadOf "https://git.vdb.to/"
+      - name: Build package
+        run: go build .
+      - name: Run server
+        env:
+          DATABASE_TYPE: postgres
+          LEVELDB_PATH: ./fixture/chaindata
+          LEVELDB_ANCIENT: ./fixture/chaindata/ancient
+          LOG_FILE_PATH: ./server-log
+        run: |
+          ./eth-statediff-service --config ./test/ci-config.toml serve &
+
+        # Run a sanity test against the fixture data
+        # Complete integration tests are TODO
+      - name: Run test
+        run: |
+          ./scripts/request-range.sh 0 32 || (E=$?; cat ./server-log; exit $E)
+
+          until grep "Finished processing block 32" ./server-log
+          do sleep 1; done
+
+          count_results() {
+              query="select count(*) from $1;"
+              docker exec -e PGPASSWORD=password test-ipld-eth-db-1 \
+                  psql -tA cerc_testing -U vdbm -c "$query"
+          }
+          set -x
+          [[ "$(count_results eth.header_cids)" = 33 ]]
+          [[ "$(count_results eth.state_cids)" = 21 ]]
+          [[ "$(count_results eth.storage_cids)" = 18 ]]

.github/workflows/issues-notion-sync.yml

@@ -1,29 +0,0 @@
-name: Notion Sync
-
-on:
-  workflow_dispatch:
-  issues:
-    types:
-      [
-        opened,
-        edited,
-        labeled,
-        unlabeled,
-        assigned,
-        unassigned,
-        milestoned,
-        demilestoned,
-        reopened,
-        closed,
-      ]
-
-jobs:
-  notion_job:
-    runs-on: ubuntu-latest
-    name: Add GitHub Issues to Notion
-    steps:
-      - name: Add GitHub Issues to Notion
-        uses: vulcanize/notion-github-action@v1.2.4-issueid
-        with:
-          notion-token: ${{ secrets.NOTION_TOKEN }}
-          notion-db: ${{ secrets.NOTION_DATABASE }}

.github/workflows/on-pr.yaml

@@ -1,7 +0,0 @@
-name: Docker Build
-
-on: [pull_request]
-
-jobs:
-  run-tests:
-    uses: ./.github/workflows/tests.yml

.github/workflows/publish.yaml

@@ -1,44 +0,0 @@
-name: Publish Docker image
-on:
-  release:
-    types: [published]
-jobs:
-  run-tests:
-    uses: ./.github/workflows/tests.yml
-  build:
-    name: Run docker build
-    runs-on: ubuntu-latest
-    needs: run-tests
-    steps:
-      - uses: actions/checkout@v2
-      - name: Get the version
-        id: vars
-        run: echo ::set-output name=sha::$(echo ${GITHUB_SHA:0:7})
-      - name: Run docker build
-        run: make docker-build
-      - name: Tag docker image
-        run: docker tag vulcanize/eth-statediff-service docker.pkg.github.com/vulcanize/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.sha}}
-      - name: Docker Login
-        run: echo ${{ secrets.GITHUB_TOKEN }} | docker login https://docker.pkg.github.com -u vulcanize --password-stdin
-      - name: Docker Push
-        run: docker push docker.pkg.github.com/vulcanize/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.sha}}
-  push_to_registries:
-    name: Push Docker image to Docker Hub
-    runs-on: ubuntu-latest
-    needs: build
-    steps:
-      - name: Get the version
-        id: vars
-        run: |
-          echo ::set-output name=sha::$(echo ${GITHUB_SHA:0:7})
-          echo ::set-output name=tag::$(echo ${GITHUB_REF#refs/tags/})
-      - name: Docker Login to Github Registry
-        run: echo ${{ secrets.GITHUB_TOKEN }} | docker login https://docker.pkg.github.com -u vulcanize --password-stdin
-      - name: Docker Pull
-        run: docker pull docker.pkg.github.com/vulcanize/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.sha}}
-      - name: Docker Login to Docker Registry
-        run: echo ${{ secrets.VULCANIZEJENKINS_PAT }} | docker login -u vulcanizejenkins --password-stdin
-      - name: Tag docker image
-        run: docker tag docker.pkg.github.com/vulcanize/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.sha}} vulcanize/eth-statediff-service:${{steps.vars.outputs.tag}}
-      - name: Docker Push to Docker Hub
-        run: docker push vulcanize/eth-statediff-service:${{steps.vars.outputs.tag}}

.github/workflows/tests.yml

@@ -1,37 +0,0 @@
-name: Tests for Geth that are used in multiple jobs.
-
-on:
-  workflow_call:
-
-env:
-  GOPATH: /tmp/go
-
-jobs:
-  build:
-    name: Run docker build
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - name: Run docker build
-        run: make docker-build
-
-  statediff-unit-test:
-    name: Run statediff unit tests
-    runs-on: ubuntu-latest
-    env:
-      GO111MODULE: on
-    steps:
-      - name: Create GOPATH
-        run: mkdir -p /tmp/go
-
-      - uses: actions/setup-go@v3
-        with:
-          go-version: ">=1.18.0"
-          check-latest: true
-
-      - name: Checkout code
-        uses: actions/checkout@v2
-
-      - name: Run unit tests
-        run: |
-          make test

.gitignore

@@ -1,2 +1,3 @@
 .idea/
 eth-statediff-service
+.vscode

Dockerfile

@@ -1,21 +1,24 @@
-FROM golang:1.18-alpine as builder
+FROM golang:1.19-alpine as builder
 
-RUN apk --update --no-cache add make git g++ linux-headers
+RUN apk add --no-cache git gcc musl-dev binutils-gold
 # DEBUG
 RUN apk add busybox-extras
 
-# Get and build ipfs-blockchain-watcher
-ADD . /go/src/github.com/vulcanize/eth-statediff-service
-#RUN git clone https://github.com/vulcanize/eth-statediff-service.git /go/src/github.com/vulcanize/eth-statediff-service
+WORKDIR /eth-statediff-service
 
-WORKDIR /go/src/github.com/vulcanize/eth-statediff-service
-RUN GO111MODULE=on CGO_ENABLED=0 GOOS=linux go build -a -installsuffix cgo -ldflags '-extldflags "-static"' -o eth-statediff-service .
+ARG GIT_VDBTO_TOKEN
+
+COPY go.mod go.sum ./
+RUN if [ -n "$GIT_VDBTO_TOKEN" ]; then git config --global url."https://$GIT_VDBTO_TOKEN:@git.vdb.to/".insteadOf "https://git.vdb.to/"; fi && \
+    go mod download && \
+    rm -f ~/.gitconfig
+COPY . .
+
+RUN go build -ldflags '-extldflags "-static"' -o eth-statediff-service .
 
-# app container
 FROM alpine
 
 ARG USER="vdbm"
-ARG CONFIG_FILE="./environments/docker.toml"
 ARG EXPOSE_PORT=8545
 
 RUN adduser -Du 5000 $USER adm
@@ -27,12 +30,11 @@ USER $USER
 
 # chown first so dir is writable
 # note: using $USER is merged, but not in the stable release yet
-COPY --chown=5000:5000 --from=builder /go/src/github.com/vulcanize/eth-statediff-service/$CONFIG_FILE config.toml
-COPY --chown=5000:5000 --from=builder /go/src/github.com/vulcanize/eth-statediff-service/startup_script.sh .
-COPY --chown=5000:5000 --from=builder /go/src/github.com/vulcanize/eth-statediff-service/environments environments
+COPY --chown=5000:5000 --from=builder /eth-statediff-service/startup_script.sh .
+COPY --chown=5000:5000 --from=builder /eth-statediff-service/environments environments
 
 # keep binaries immutable
-COPY --from=builder /go/src/github.com/vulcanize/eth-statediff-service/eth-statediff-service eth-statediff-service
+COPY --from=builder /eth-statediff-service/eth-statediff-service eth-statediff-service
 
 EXPOSE $EXPOSE_PORT
 

README.md

@@ -1,17 +1,25 @@
 # eth-statediff-service
 
-[![Go Report Card](https://goreportcard.com/badge/github.com/vulcanize/eth-statediff-service)](https://goreportcard.com/report/github.com/vulcanize/eth-statediff-service)
+[![Go Report Card](https://goreportcard.com/badge/github.com/cerc-io/eth-statediff-service)](https://goreportcard.com/report/github.com/cerc-io/eth-statediff-service)
 
->> standalone statediffing service ontop of LevelDB
-
-Purpose:
-
-Stand up a statediffing service directly on top of a go-ethereum LevelDB instance.
+A standalone statediffing service which runs directly on top of a `go-ethereum` LevelDB instance.
 This service can serve historical state data over the same rpc interface as
-[statediffing geth](https://github.com/vulcanize/go-ethereum/releases/tag/v1.9.11-statediff-0.0.5) without needing to run a full node
+[statediffing geth](https://github.com/cerc-io/go-ethereum) without needing to run a full node.
+
+## Setup
+
+Configure access to the private Git server at `git.vdb.to`, then build the executable:
+
+```bash
+go build .
+```
 
 ## Configuration
 
+See [./environments/example.toml](./environments/example.toml) for an annotated example config file.
+
+### Local Setup
+
 * Create a chain config file `chain.json` according to chain config in genesis json file used by local geth.
 
   Example:
@@ -34,72 +42,19 @@ This service can serve historical state data over the same rpc interface as
   }
   ```
 
-* Sample database and chain configuration (from [environments/config.toml](./environments/config.toml)):
-
-    ```toml
-    [leveldb]
-        mode = "local"
-        # Path to geth LevelDB data
-        path = "/path-to-local-geth-data/chaindata"
-        ancient = "/path-to-local-geth-data/chaindata/ancient"
-
-    [ethereum]
-        chainConfig = "./chain.json" # Path to custom chain config file
-        chainID = 41337              # Same chain ID as in chain.json
-
-    [database]
-        # Update database config
-        name     = "vulcanize_testing"
-        hostname = "localhost"
-        port     = 5432
-        user     = "postgres"
-        password = "postgres"
-        type = "postgres"
-    ```
-
-* Service and metrics configuration:
-
-    ```toml
-    [statediff]
-        serviceWorkers = 1     # Number of diffs to process concurrently
-        workerQueueSize = 1024 # Size of buffer for block range requests
-        trieWorkers = 4        # Number of state subtries to process concurrently
-
-    [cache]
-        database = 1024        # Trie node cache size in MB
-        trie = 1024            # LevelDB cache size in MiB
-
-    [prom]
-        dbStats = false
-        metrics = true
-        http = true
-        httpAddr = "localhost"
-        httpPort = "8889"
-    ```
-
-* To use a remote LevelDB RPC endpoint change the following in [config file](./environments/config.toml)
-    ```toml
-    [leveldb]
-        mode = "remote"
-        url = "http://127.0.0.1:8082/" # Remote LevelDB RPC url
-    ```
-
-* When using the `run` command to write diffs for specific block ranges, add this:
-    ```toml
-    [run]
-        only = false
-        ranges = [
-            [8, 15] # Block number range for which to write statediff.
-        ]
-    ```
+  Provide the path to the above file in the config.
 
 ## Usage
 
+* Create / update the config file (refer to example config above).
+
 ### `serve`
 
-To serve state diffs over RPC:
+* To serve the statediff RPC API:
 
-`eth-statediff-service serve --config=<config path>`
+    ```bash
+    ./eth-statediff-service serve --config=<config path>
+    ```
 
     Example:
 
@@ -107,19 +62,151 @@ Example:
     ./eth-statediff-service serve --config environments/config.toml
     ```
 
-Available RPC methods are:
+* Available RPC methods:
+    * `statediff_stateTrieAt()`
+    * `statediff_streamCodeAndCodeHash()`
     * `statediff_stateDiffAt()`
     * `statediff_writeStateDiffAt()`
     * `statediff_writeStateDiffsInRange()`
 
-e.g. `curl -X POST -H 'Content-Type: application/json' --data '{"jsonrpc":"2.0","method":"statediff_writeStateDiffsInRange","params":['"$BEGIN"', '"$END"', {"includeBlock":true,"includeReceipts":true,"includeTD":true,"includeCode":true}],"id":1}' "$HOST":"$PORT"`
+    Example:
 
-### `run`
+    ```bash
+    curl -X POST -H 'Content-Type: application/json' --data '{
+      "jsonrpc": "2.0",
+      "method": "statediff_writeStateDiffsInRange",
+      "params": [0, 1, {
+          "ncludeBlock": true,
+          "includeReceipts": true,
+          "includeTD": true,
+          "includeCode": true
+        }
+      ],
+      "id": 1
+    }' "$HOST":"$PORT"
+    ```
 
-Produces diffs for specific block ranges.
+* Prerun:
+    * The process can be configured locally with sets of ranges to process as a "prerun" to
+      processing directed by the server endpoints.
+    * This is done by turning "prerun" on in the config (`statediff.prerun = true`) and defining
+ranges and params in the `prerun` section of the config.
+    * Set the range using `prerun.start` and `prerun.stop`. Use `prerun.ranges` if prerun on more
+      than one range is required.
+
+* NOTE: Currently, `params.includeTD` must be set to / passed as `true`.
+
+## Monitoring
+
+* Enable metrics using config parameters `prom.metrics` and `prom.http`.
+* `eth-statediff-service` exposes following prometheus metrics at `/metrics` endpoint:
+    * `ranges_queued`: Number of range requests currently queued.
+    * `loaded_height`: The last block that was loaded for processing.
+    * `processed_height`: The last block that was processed.
+    * `stats.t_block_load`: Block loading time.
+    * `stats.t_block_processing`: Block (header, uncles, txs, rcts, tx trie, rct trie) processing time.
+    * `stats.t_state_processing`: State (state trie, storage tries, and code) processing time.
+    * `stats.t_postgres_tx_commit`: Postgres tx commit time.
+    * `http.count`: HTTP request count.
+    * `http.duration`: HTTP request duration.
+    * `ipc.count`: Unix socket connection count.
+
+## Tests
+
+* Run unit tests:
+
+    ```bash
+    make test
+    ```
+
+## Import output data in file mode into a database
+
+* When `eth-statediff-service` is run in file mode (`database.type`: `file`) the output is in form of a SQL
+  file or multiple CSV files.
+
+### SQL
+
+* Assuming the output files are located in host's `./output_dir` directory.
+
+* Create a directory to store post-processed output:
+
+    ```bash
+    mkdir -p output_dir/processed_output
+    ```
+
+* (Optional) Get row counts in the output:
+
+    ```bash
+    wc -l output_dir/statediff.sql > output_stats.txt
+    ```
+
+* De-duplicate data:
+
+    ```bash
+    sort -u output_dir/statediff.sql -o output_dir/processed_output/deduped-statediff.sql
+    ```
+
+* Copy over the post-processed output files to the DB server (say in `/output_dir`).
+
+* Run the following to import data:
+
+    ```bash
+    psql -U <DATABASE_USER> -h <DATABASE_HOSTNAME> -p <DATABASE_PORT> <DATABASE_NAME> --set ON_ERROR_STOP=on -f /output_dir/processed_output/deduped-statediff.sql
+    ```
+
+### CSV
+
+* Create an env file with the required variables. Refer [.sample.env](./scripts/.sample.env).
+
+* (Optional) Get row counts in the output:
+
+    ```bash
+    ./scripts/count-lines.sh <ENV_FILE_PATH>
+    ```
+
+* De-duplicate data:
+
+    ```bash
+    ./scripts/dedup.sh <ENV_FILE_PATH>
+    ```
+
+* Perform column checks:
+
+    ```bash
+    ./scripts/check-columns.sh <ENV_FILE_PATH>
+    ```
+
+    Check the output logs for any rows detected with unexpected number of columns.
 
     Example:
 
     ```bash
-./eth-statediff-service run --config environments/config.toml --run.ranges '[8,15]'
+    # log
+    eth.header_cids
+    Start: Wednesday 21 September 2022 06:00:38 PM IST
+    Time taken: 00:00:05
+    End: Wednesday 21 September 2022 06:00:43 PM IST
+    Total bad rows: 1 ./check-columns/eth.header_cids.txt
+
+    # bad row output
+    # line number, num. of columns, data
+    23 17 22,xxxxxx,0x07f5ea5c94aa8dea60b28f6b6315d92f2b6d78ca4b74ea409adeb191b5a114f2,0x5918487321aa57dd0c50977856c6231e7c4ee79e95b694c7c8830227d77a1ecc,bagiacgzaa726uxeuvkg6uyfsr5vwgfozf4vw26gkjn2ouqe232yzdnnbctza,45,geth,0,0xad8fa8df61b98dbda7acd6ca76d5ce4cbba663d5f608cc940957adcdb94cee8d,0xc621412320a20b4aaff5363bdf063b9d13e394ef82e55689ab703aae5db08e26,0x71ec1c7d81269ce115be81c81f13e1cc2601c292a7f20440a77257ecfdc69940,0x1dcc4de8dec75d7aab85b567b6ccd41ad312451b948a7413f0a142fd40d49347,\x2000000000000000000000000000000000000000000000000000020000000000000000000000000000000000000000000000000000000000000000000,1658408419,/blocks/DMQAP5PKLSKKVDPKMCZI623DCXMS6K3NPDFEW5HKICNN5MMRWWQRJ4Q,1,0x0000000000000000000000000000000000000000
     ```
+
+* Import data using `timescaledb-parallel-copy`:  
+  (requires [`timescaledb-parallel-copy`](https://github.com/timescale/timescaledb-parallel-copy) installation; readily comes with TimescaleDB docker image)
+
+    ```bash
+    ./scripts/timescaledb-import.sh <ENV_FILE_PATH>
+    ```
+
+* NOTE: `COPY` command on CSVs inserts empty strings as `NULL` in the DB. Passing `FORCE_NOT_NULL <COLUMN_NAME>` forces it to insert empty strings instead. This is required to maintain compatibility of the imported statediff data with the data generated in `postgres` mode. Reference: https://www.postgresql.org/docs/14/sql-copy.html
+
+### Stats
+
+The binary includes a `stats` command which reports stats for the offline or remote levelDB.
+
+At this time, the only stat supported is to return the latest/highest block height and hash found the levelDB, this is
+useful for determining what the upper limit is for a standalone statediffing process on a given levelDB.
+
+`./eth-statediff-service stats --config={path to toml config file}`

cmd/env.go

@@ -30,11 +30,12 @@ const (
 
 	DB_CACHE_SIZE_MB   = "DB_CACHE_SIZE_MB"
 	TRIE_CACHE_SIZE_MB = "TRIE_CACHE_SIZE_MB"
-	LVLDB_MODE         = "LVLDB_MODE"
-	LVLDB_PATH         = "LVLDB_PATH"
-	LVLDB_ANCIENT      = "LVLDB_ANCIENT"
-	LVLDB_URL          = "LVLDB_URL"
+	LEVELDB_MODE       = "LEVELDB_MODE"
+	LEVELDB_PATH       = "LEVELDB_PATH"
+	LEVELDB_ANCIENT    = "LEVELDB_ANCIENT"
+	LEVELDB_URL        = "LEVELDB_URL"
 
+	STATEDIFF_PRERUN            = "STATEDIFF_PRERUN"
 	STATEDIFF_TRIE_WORKERS      = "STATEDIFF_TRIE_WORKERS"
 	STATEDIFF_SERVICE_WORKERS   = "STATEDIFF_SERVICE_WORKERS"
 	STATEDIFF_WORKER_QUEUE_SIZE = "STATEDIFF_WORKER_QUEUE_SIZE"
@@ -48,10 +49,14 @@ const (
 	PROM_HTTP_PORT = "PROM_HTTP_PORT"
 	PROM_DB_STATS  = "PROM_DB_STATS"
 
-	RUN_INCLUDE_BLOCK    = "RUN_INCLUDE_BLOCK"
-	RUN_INCLUDE_RECEIPTS = "RUN_INCLUDE_RECEIPTS"
-	RUN_INCLUDE_TD       = "RUN_INCLUDE_TD"
-	RUN_INCLUDE_CODE     = "RUN_INCLUDE_CODE"
+	PRERUN_ONLY             = "PRERUN_ONLY"
+	PRERUN_PARALLEL         = "PRERUN_PARALLEL"
+	PRERUN_RANGE_START      = "PRERUN_RANGE_START"
+	PRERUN_RANGE_STOP       = "PRERUN_RANGE_STOP"
+	PRERUN_INCLUDE_BLOCK    = "PRERUN_INCLUDE_BLOCK"
+	PRERUN_INCLUDE_RECEIPTS = "PRERUN_INCLUDE_RECEIPTS"
+	PRERUN_INCLUDE_TD       = "PRERUN_INCLUDE_TD"
+	PRERUN_INCLUDE_CODE     = "PRERUN_INCLUDE_CODE"
 
 	LOG_LEVEL     = "LOG_LEVEL"
 	LOG_FILE_PATH = "LOG_FILE_PATH"
@@ -66,6 +71,8 @@ const (
 	DATABASE_DRIVER_TYPE  = "DATABASE_DRIVER_TYPE"
 	DATABASE_DUMP_DST     = "DATABASE_DUMP_DST"
 	DATABASE_FILE_PATH    = "DATABASE_FILE_PATH"
+	DATABASE_FILE_MODE    = "DATABASE_FILE_MODE"
+	DATABASE_FILE_CSV_DIR = "DATABASE_FILE_CSV_DIR"
 
 	DATABASE_MAX_IDLE_CONNECTIONS = "DATABASE_MAX_IDLE_CONNECTIONS"
 	DATABASE_MAX_OPEN_CONNECTIONS = "DATABASE_MAX_OPEN_CONNECTIONS"
@@ -73,6 +80,8 @@ const (
 	DATABASE_MAX_CONN_LIFETIME    = "DATABASE_MAX_CONN_LIFETIME"
 	DATABASE_CONN_TIMEOUT         = "DATABSE_CONN_TIMEOUT"
 	DATABASE_MAX_CONN_IDLE_TIME   = "DATABASE_MAX_CONN_IDLE_TIME"
+
+	DEBUG_PPROF = "DEBUG_PPROF"
 )
 
 // Bind env vars for eth node and DB configuration
@@ -103,15 +112,17 @@ func init() {
 	viper.BindEnv("database.type", DATABASE_TYPE)
 	viper.BindEnv("database.driver", DATABASE_DRIVER_TYPE)
 	viper.BindEnv("database.dumpDestination", DATABASE_DUMP_DST)
+	viper.BindEnv("database.fileMode", DATABASE_FILE_MODE)
 	viper.BindEnv("database.filePath", DATABASE_FILE_PATH)
+	viper.BindEnv("database.fileCsvDir", DATABASE_FILE_CSV_DIR)
 
 	viper.BindEnv("cache.database", DB_CACHE_SIZE_MB)
 	viper.BindEnv("cache.trie", TRIE_CACHE_SIZE_MB)
 
-	viper.BindEnv("leveldb.mode", LVLDB_MODE)
-	viper.BindEnv("leveldb.path", LVLDB_PATH)
-	viper.BindEnv("leveldb.ancient", LVLDB_ANCIENT)
-	viper.BindEnv("leveldb.url", LVLDB_URL)
+	viper.BindEnv("leveldb.mode", LEVELDB_MODE)
+	viper.BindEnv("leveldb.path", LEVELDB_PATH)
+	viper.BindEnv("leveldb.ancient", LEVELDB_ANCIENT)
+	viper.BindEnv("leveldb.url", LEVELDB_URL)
 
 	viper.BindEnv("prom.metrics", PROM_METRICS)
 	viper.BindEnv("prom.http", PROM_HTTP)
@@ -123,11 +134,18 @@ func init() {
 	viper.BindEnv("statediff.trieWorkers", STATEDIFF_TRIE_WORKERS)
 	viper.BindEnv("statediff.workerQueueSize", STATEDIFF_WORKER_QUEUE_SIZE)
 
-	viper.BindEnv("run.params.includeBlock", RUN_INCLUDE_BLOCK)
-	viper.BindEnv("run.params.includeReceipts", RUN_INCLUDE_RECEIPTS)
-	viper.BindEnv("run.params.includeTD", RUN_INCLUDE_TD)
-	viper.BindEnv("run.params.includeCode", RUN_INCLUDE_CODE)
+	viper.BindEnv("statediff.prerun", STATEDIFF_PRERUN)
+	viper.BindEnv("prerun.only", PRERUN_ONLY)
+	viper.BindEnv("prerun.parallel", PRERUN_PARALLEL)
+	viper.BindEnv("prerun.start", PRERUN_RANGE_START)
+	viper.BindEnv("prerun.stop", PRERUN_RANGE_STOP)
+	viper.BindEnv("prerun.params.includeBlock", PRERUN_INCLUDE_BLOCK)
+	viper.BindEnv("prerun.params.includeReceipts", PRERUN_INCLUDE_RECEIPTS)
+	viper.BindEnv("prerun.params.includeTD", PRERUN_INCLUDE_TD)
+	viper.BindEnv("prerun.params.includeCode", PRERUN_INCLUDE_CODE)
 
 	viper.BindEnv("log.level", LOG_LEVEL)
 	viper.BindEnv("log.file", LOG_FILE_PATH)
+
+	viper.BindEnv("debug.pprof", DEBUG_PPROF)
 }

cmd/root.go

@@ -34,7 +34,7 @@ import (
 	"github.com/spf13/cobra"
 	"github.com/spf13/viper"
 
-	"github.com/vulcanize/eth-statediff-service/pkg/prom"
+	"github.com/cerc-io/eth-statediff-service/pkg/prom"
 )
 
 var (
@@ -45,7 +45,7 @@ var (
 
 var rootCmd = &cobra.Command{
 	Use:              "eth-statediff-service",
-	PersistentPreRun: setupLoggingAndMetrics,
+	PersistentPreRun: initFuncs,
 }
 
 func Execute() {
@@ -54,7 +54,7 @@ func Execute() {
 	}
 }
 
-func setupLoggingAndMetrics(cmd *cobra.Command, args []string) {
+func initFuncs(cmd *cobra.Command, args []string) {
 	logfile := viper.GetString("log.file")
 	if logfile != "" {
 		file, err := os.OpenFile(logfile,
@@ -120,11 +120,12 @@ func init() {
 	rootCmd.PersistentFlags().String("ancient-path", "", "path to ancient datastore")
 	rootCmd.PersistentFlags().String("leveldb-url", "", "url to primary leveldb-ethdb-rpc server")
 
+	rootCmd.PersistentFlags().Bool("prerun", false, "turn on prerun of toml configured ranges")
 	rootCmd.PersistentFlags().Int("service-workers", 0, "number of range requests to process concurrently")
 	rootCmd.PersistentFlags().Int("trie-workers", 0, "number of workers to use for trie traversal and processing")
 	rootCmd.PersistentFlags().Int("worker-queue-size", 0, "size of the range request queue for service workers")
 
-	rootCmd.PersistentFlags().String("database-name", "vulcanize_public", "database name")
+	rootCmd.PersistentFlags().String("database-name", "cerc_public", "database name")
 	rootCmd.PersistentFlags().Int("database-port", 5432, "database port")
 	rootCmd.PersistentFlags().String("database-hostname", "localhost", "database hostname")
 	rootCmd.PersistentFlags().String("database-user", "", "database user")
@@ -138,7 +139,9 @@ func init() {
 	rootCmd.PersistentFlags().String("database-type", "postgres", "database type (currently supported: postgres, dump)")
 	rootCmd.PersistentFlags().String("database-driver", "sqlx", "database driver type (currently supported: sqlx, pgx)")
 	rootCmd.PersistentFlags().String("database-dump-dst", "stdout", "dump destination (for database-type=dump; options: stdout, stderr, discard)")
-	rootCmd.PersistentFlags().String("database-file-path", "", "full file path (for database-type=file)")
+	rootCmd.PersistentFlags().String("database-file-mode", "csv", "mode for writing file (for database-type=file; options: csv, sql)")
+	rootCmd.PersistentFlags().String("database-file-csv-dir", "", "full directory path (for database-file-mode=csv)")
+	rootCmd.PersistentFlags().String("database-file-path", "", "full file path (for database-file-mode=sql)")
 
 	rootCmd.PersistentFlags().String("eth-node-id", "", "eth node id")
 	rootCmd.PersistentFlags().String("eth-client-name", "eth-statediff-service", "eth client name")
@@ -156,10 +159,13 @@ func init() {
 	rootCmd.PersistentFlags().Bool("prom-db-stats", false, "enables prometheus db stats")
 	rootCmd.PersistentFlags().Bool("prom-metrics", false, "enable prometheus metrics")
 
-	rootCmd.PersistentFlags().Bool("run-include-block", true, "include block data in the statediff payload")
-	rootCmd.PersistentFlags().Bool("run-include-receipts", true, "include receipts in the statediff payload")
-	rootCmd.PersistentFlags().Bool("run-include-td", true, "include td in the statediff payload")
-	rootCmd.PersistentFlags().Bool("run-include-code", true, "include code and codehash mappings in statediff payload")
+	rootCmd.PersistentFlags().Bool("prerun-only", false, "only process pre-configured ranges; exit afterwards")
+	rootCmd.PersistentFlags().Int("prerun-start", 0, "start height for a prerun range")
+	rootCmd.PersistentFlags().Int("prerun-stop", 0, "stop height for a prerun range")
+	rootCmd.PersistentFlags().Bool("prerun-include-block", true, "include block data in the statediff payload")
+	rootCmd.PersistentFlags().Bool("prerun-include-receipts", true, "include receipts in the statediff payload")
+	rootCmd.PersistentFlags().Bool("prerun-include-td", true, "include td in the statediff payload")
+	rootCmd.PersistentFlags().Bool("prerun-include-code", true, "include code and codehash mappings in statediff payload")
 
 	viper.BindPFlag("server.httpPath", rootCmd.PersistentFlags().Lookup("http-path"))
 	viper.BindPFlag("server.ipcPath", rootCmd.PersistentFlags().Lookup("ipc-path"))
@@ -167,6 +173,7 @@ func init() {
 	viper.BindPFlag("log.file", rootCmd.PersistentFlags().Lookup("log-file"))
 	viper.BindPFlag("log.level", rootCmd.PersistentFlags().Lookup("log-level"))
 
+	viper.BindPFlag("statediff.prerun", rootCmd.PersistentFlags().Lookup("prerun"))
 	viper.BindPFlag("statediff.serviceWorkers", rootCmd.PersistentFlags().Lookup("service-workers"))
 	viper.BindPFlag("statediff.trieWorkers", rootCmd.PersistentFlags().Lookup("trie-workers"))
 	viper.BindPFlag("statediff.workerQueueSize", rootCmd.PersistentFlags().Lookup("worker-queue-size"))
@@ -190,6 +197,8 @@ func init() {
 	viper.BindPFlag("database.type", rootCmd.PersistentFlags().Lookup("database-type"))
 	viper.BindPFlag("database.driver", rootCmd.PersistentFlags().Lookup("database-driver"))
 	viper.BindPFlag("database.dumpDestination", rootCmd.PersistentFlags().Lookup("database-dump-dst"))
+	viper.BindPFlag("database.fileMode", rootCmd.PersistentFlags().Lookup("database-file-mode"))
+	viper.BindPFlag("database.fileCsvDir", rootCmd.PersistentFlags().Lookup("database-file-csv-dir"))
 	viper.BindPFlag("database.filePath", rootCmd.PersistentFlags().Lookup("database-file-path"))
 
 	viper.BindPFlag("ethereum.nodeID", rootCmd.PersistentFlags().Lookup("eth-node-id"))
@@ -208,10 +217,16 @@ func init() {
 	viper.BindPFlag("prom.dbStats", rootCmd.PersistentFlags().Lookup("prom-db-stats"))
 	viper.BindPFlag("prom.metrics", rootCmd.PersistentFlags().Lookup("prom-metrics"))
 
-	viper.BindPFlag("run.params.includeBlock", rootCmd.PersistentFlags().Lookup("run-include-block"))
-	viper.BindPFlag("run.params.includeReceipts", rootCmd.PersistentFlags().Lookup("run-include-receipts"))
-	viper.BindPFlag("run.params.includeTD", rootCmd.PersistentFlags().Lookup("run-include-td"))
-	viper.BindPFlag("run.params.includeCode", rootCmd.PersistentFlags().Lookup("run-include-code"))
+	viper.BindPFlag("prerun.only", rootCmd.PersistentFlags().Lookup("prerun-only"))
+	viper.BindPFlag("prerun.parallel", rootCmd.PersistentFlags().Lookup("prerun-parallel"))
+	viper.BindPFlag("prerun.start", rootCmd.PersistentFlags().Lookup("prerun-start"))
+	viper.BindPFlag("prerun.stop", rootCmd.PersistentFlags().Lookup("prerun-stop"))
+	viper.BindPFlag("prerun.params.includeBlock", rootCmd.PersistentFlags().Lookup("prerun-include-block"))
+	viper.BindPFlag("prerun.params.includeReceipts", rootCmd.PersistentFlags().Lookup("prerun-include-receipts"))
+	viper.BindPFlag("prerun.params.includeTD", rootCmd.PersistentFlags().Lookup("prerun-include-td"))
+	viper.BindPFlag("prerun.params.includeCode", rootCmd.PersistentFlags().Lookup("prerun-include-code"))
+
+	viper.BindPFlag("debug.pprof", rootCmd.PersistentFlags().Lookup("debug-pprof"))
 
 	rand.Seed(time.Now().UnixNano())
 }
@@ -284,18 +299,35 @@ func getConfig(nodeInfo node.Info) (interfaces.Config, error) {
 	if err != nil {
 		return nil, err
 	}
-	logWithCommand.Infof("configuring service for database type: %s", dbType)
+	logWithCommand.Debugf("Configuring service for database type: %s", dbType)
 	var indexerConfig interfaces.Config
 	switch dbType {
 	case shared.FILE:
-		logWithCommand.Info("starting in sql file writing mode")
-		filePathStr := viper.GetString("database.filePath")
-		if filePathStr == "" {
-			logWithCommand.Fatal("when operating in sql file writing mode a file path must be provided")
+		logWithCommand.Info("Starting in sql file writing mode")
+
+		fileModeStr := viper.GetString("database.fileMode")
+		fileMode, err := file.ResolveFileMode(fileModeStr)
+		if err != nil {
+			utils.Fatalf("%v", err)
+		}
+
+		filePathStr := viper.GetString("database.filePath")
+		if fileMode == file.SQL && filePathStr == "" {
+			logWithCommand.Fatal("When operating in sql file writing mode a file path must be provided")
+		}
+
+		fileCsvDirStr := viper.GetString("database.fileCsvDir")
+		if fileMode == file.CSV && fileCsvDirStr == "" {
+			logWithCommand.Fatal("When operating in csv file writing mode a directory path must be provided")
+		}
+
+		indexerConfig = file.Config{
+			Mode:      fileMode,
+			OutputDir: fileCsvDirStr,
+			FilePath:  filePathStr,
 		}
-		indexerConfig = file.Config{FilePath: filePathStr}
 	case shared.DUMP:
-		logWithCommand.Info("starting in data dump mode")
+		logWithCommand.Info("Starting in data dump mode")
 		dumpDstStr := viper.GetString("database.dumpDestination")
 		dumpDst, err := dump.ResolveDumpType(dumpDstStr)
 		if err != nil {
@@ -312,7 +344,7 @@ func getConfig(nodeInfo node.Info) (interfaces.Config, error) {
 			return nil, fmt.Errorf("unrecognized dump destination: %s", dumpDst)
 		}
 	case shared.POSTGRES:
-		logWithCommand.Info("starting in postgres mode")
+		logWithCommand.Info("Starting in postgres mode")
 		driverTypeStr := viper.GetString("database.driver")
 		driverType, err := postgres.ResolveDriverType(driverTypeStr)
 		if err != nil {
@@ -324,8 +356,6 @@ func getConfig(nodeInfo node.Info) (interfaces.Config, error) {
 			DatabaseName: viper.GetString("database.name"),
 			Username:     viper.GetString("database.user"),
 			Password:     viper.GetString("database.password"),
-			ID:           nodeInfo.ID,
-			ClientName:   nodeInfo.ClientName,
 			Driver:       driverType,
 		}
 		if viper.IsSet("database.maxIdle") {

cmd/run.go

@@ -1,91 +0,0 @@
-// Copyright © 2023 Vulcanize, Inc
-//
-// This program is free software: you can redistribute it and/or modify
-// it under the terms of the GNU Affero General Public License as published by
-// the Free Software Foundation, either version 3 of the License, or
-// (at your option) any later version.
-//
-// This program is distributed in the hope that it will be useful,
-// but WITHOUT ANY WARRANTY; without even the implied warranty of
-// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-// GNU Affero General Public License for more details.
-//
-// You should have received a copy of the GNU Affero General Public License
-// along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-package cmd
-
-import (
-	"os"
-	"os/signal"
-	"sync"
-
-	statediff "github.com/cerc-io/plugeth-statediff"
-	"github.com/ethereum/go-ethereum/common"
-	"github.com/sirupsen/logrus"
-	"github.com/spf13/cobra"
-	"github.com/spf13/viper"
-
-	pkg "github.com/vulcanize/eth-statediff-service/pkg"
-)
-
-// serveCmd represents the serve command
-var runCmd = &cobra.Command{
-	Use:   "run",
-	Short: "Produce diffs for a specific block range",
-	Long: `Usage
-
-./eth-statediff-service run --config={path to toml config file}`,
-	Run: func(cmd *cobra.Command, args []string) {
-		subCommand = cmd.CalledAs()
-		logWithCommand = *logrus.WithField("SubCommand", subCommand)
-		runRanges()
-	},
-}
-
-func init() {
-	rootCmd.AddCommand(runCmd)
-}
-
-func runRanges() {
-	service := createStateDiffService()
-	// start service and servers
-	var wg sync.WaitGroup
-	ranges := getConfiguredRanges()
-	service.Run(ranges)
-
-	// clean shutdown
-	shutdown := make(chan os.Signal)
-	signal.Notify(shutdown, os.Interrupt)
-	<-shutdown
-	logWithCommand.Info("Received interrupt signal, shutting down")
-	service.Stop()
-	wg.Wait()
-}
-
-func getConfiguredRanges() []pkg.RangeRequest {
-	params := statediff.Params{
-		IncludeBlock:    viper.GetBool("run.params.includeBlock"),
-		IncludeReceipts: viper.GetBool("run.params.includeReceipts"),
-		IncludeTD:       viper.GetBool("run.params.includeTD"),
-		IncludeCode:     viper.GetBool("run.params.includeCode"),
-	}
-	var addrStrs []string
-	viper.UnmarshalKey("run.params.watchedAddresses", &addrStrs)
-	addrs := make([]common.Address, len(addrStrs))
-	for i, addrStr := range addrStrs {
-		addrs[i] = common.HexToAddress(addrStr)
-	}
-	params.WatchedAddresses = addrs
-	var rawRanges []blockRange
-	viper.UnmarshalKey("run.ranges", &rawRanges)
-	blockRanges := make([]pkg.RangeRequest, len(rawRanges))
-	for i, rawRange := range rawRanges {
-		blockRanges[i] = pkg.RangeRequest{
-			Start:  rawRange[0],
-			Stop:   rawRange[1],
-			Params: params,
-		}
-	}
-	return blockRanges
-}

cmd/serve.go

@@ -16,8 +16,11 @@
 package cmd
 
 import (
+	"net/http"
+	_ "net/http/pprof"
 	"os"
 	"os/signal"
+	"runtime"
 	"sync"
 
 	"github.com/ethereum/go-ethereum/rpc"
@@ -25,8 +28,8 @@ import (
 	"github.com/spf13/cobra"
 	"github.com/spf13/viper"
 
-	sd "github.com/vulcanize/eth-statediff-service/pkg"
-	srpc "github.com/vulcanize/eth-statediff-service/pkg/rpc"
+	pkg "github.com/cerc-io/eth-statediff-service/pkg"
+	srpc "github.com/cerc-io/eth-statediff-service/pkg/rpc"
 )
 
 // serveCmd represents the serve command
@@ -47,22 +50,57 @@ func init() {
 	rootCmd.AddCommand(serveCmd)
 }
 
-func serve() {
-	logWithCommand.Info("Running eth-statediff-service serve command")
+func maxParallelism() int {
+	maxProcs := runtime.GOMAXPROCS(0)
+	numCPU := runtime.NumCPU()
+	if maxProcs < numCPU {
+		return maxProcs
+	}
+	return numCPU
+}
 
-	service := createStateDiffService()
+func serve() {
+	logWithCommand.Debug("Running eth-statediff-service serve command")
+	logWithCommand.Debugf("Parallelism: %d", maxParallelism())
+
+	reader, chainConf, nodeInfo := instantiateLevelDBReader()
+
+	reportLatestBlock(reader)
+
+	service, err := createStateDiffService(reader, chainConf, nodeInfo)
+	if err != nil {
+		logWithCommand.Fatal(err)
+	}
+
+	// Enable the pprof agent if configured
+	if viper.GetBool("debug.pprof") {
+		// See: https://www.farsightsecurity.com/blog/txt-record/go-remote-profiling-20161028/
+		// For security reasons: do not use the default http multiplexor elsewhere in this process.
+		go func() {
+			logWithCommand.Info("Starting pprof listener on port 6060")
+			logWithCommand.Fatal(http.ListenAndServe("localhost:6060", nil))
+		}()
+	}
+
+	// short circuit if we only want to perform prerun
+	if viper.GetBool("prerun.only") {
+		parallel := viper.GetBool("prerun.parallel")
+		if err := service.Run(nil, parallel); err != nil {
+			logWithCommand.Fatalf("Unable to perform prerun: %v", err)
+		}
+		return
+	}
 
 	// start service and servers
-	logWithCommand.Info("Starting statediff service")
 	var wg sync.WaitGroup
 	if err := service.Loop(&wg); err != nil {
 		logWithCommand.Fatalf("unable to start statediff service: %v", err)
 	}
-	logWithCommand.Info("Starting RPC servers")
+
 	if err := startServers(service); err != nil {
 		logWithCommand.Fatal(err)
 	}
-	logWithCommand.Info("RPC servers successfully spun up; awaiting requests")
+	logWithCommand.Debug("RPC servers successfully spun up; awaiting requests")
 
 	// clean shutdown
 	shutdown := make(chan os.Signal)
@@ -73,21 +111,19 @@ func serve() {
 	wg.Wait()
 }
 
-func startServers(serv *sd.Service) error {
+func startServers(serv *pkg.Service) error {
 	ipcPath := viper.GetString("server.ipcPath")
 	httpPath := viper.GetString("server.httpPath")
 	if ipcPath == "" && httpPath == "" {
-		logWithCommand.Fatal("need an ipc path and/or an http path")
+		logWithCommand.Fatal("Need an IPC path and/or an HTTP path")
 	}
 	if ipcPath != "" {
-		logWithCommand.Info("starting up IPC server")
 		_, _, err := srpc.StartIPCEndpoint(ipcPath, serv.APIs())
 		if err != nil {
 			return err
 		}
 	}
 	if httpPath != "" {
-		logWithCommand.Info("starting up HTTP server")
 		_, err := srpc.StartHTTPEndpoint(httpPath, serv.APIs(), []string{"statediff"}, nil, []string{"*"}, rpc.HTTPTimeouts{})
 		if err != nil {
 			return err

cmd/stats.go

@@ -0,0 +1,46 @@
+// Copyright © 2022 Vulcanize, Inc
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+package cmd
+
+import (
+	"github.com/sirupsen/logrus"
+	"github.com/spf13/cobra"
+)
+
+// statsCmd represents the serve command
+var statsCmd = &cobra.Command{
+	Use:   "stats",
+	Short: "Report stats for cold levelDB",
+	Long: `Usage
+
+./eth-statediff-service stats --config={path to toml config file}`,
+	Run: func(cmd *cobra.Command, args []string) {
+		subCommand = cmd.CalledAs()
+		logWithCommand = *logrus.WithField("SubCommand", subCommand)
+		stats()
+	},
+}
+
+func init() {
+	rootCmd.AddCommand(statsCmd)
+}
+
+func stats() {
+	logWithCommand.Info("Running eth-statediff-service stats command")
+
+	reader, _, _ := instantiateLevelDBReader()
+	reportLatestBlock(reader)
+}

cmd/util.go

@@ -6,20 +6,114 @@ import (
 	"fmt"
 	"os"
 
-	ind "github.com/cerc-io/plugeth-statediff/indexer"
+	statediff "github.com/cerc-io/plugeth-statediff"
+	"github.com/cerc-io/plugeth-statediff/indexer"
+	"github.com/cerc-io/plugeth-statediff/indexer/node"
+	"github.com/cerc-io/plugeth-statediff/indexer/shared"
 	"github.com/cerc-io/plugeth-statediff/utils/log"
+	"github.com/ethereum/go-ethereum/common"
 	"github.com/ethereum/go-ethereum/params"
 	"github.com/ethereum/go-ethereum/trie"
 	"github.com/spf13/viper"
 
-	sd "github.com/vulcanize/eth-statediff-service/pkg"
+	pkg "github.com/cerc-io/eth-statediff-service/pkg"
+	"github.com/cerc-io/eth-statediff-service/pkg/prom"
 )
 
 type blockRange [2]uint64
 
-func createStateDiffService() *sd.Service {
+func createStateDiffService(lvlDBReader pkg.Reader, chainConf *params.ChainConfig, nodeInfo node.Info) (*pkg.Service, error) {
+	// create statediff service
+	logWithCommand.Debug("Setting up database")
+	conf, err := getConfig(nodeInfo)
+	if err != nil {
+		logWithCommand.Fatal(err)
+	}
+
+	logWithCommand.Debug("Creating statediff indexer")
+	db, indexer, err := indexer.NewStateDiffIndexer(context.Background(), chainConf, nodeInfo, conf)
+	if err != nil {
+		logWithCommand.Fatal(err)
+	}
+	if conf.Type() == shared.POSTGRES && viper.GetBool("prom.dbStats") {
+		prom.RegisterDBCollector(viper.GetString("database.name"), db)
+	}
+
+	logWithCommand.Debug("Creating statediff service")
+	sdConf := pkg.ServiceConfig{
+		ServiceWorkers:  viper.GetUint("statediff.serviceWorkers"),
+		TrieWorkers:     viper.GetUint("statediff.trieWorkers"),
+		WorkerQueueSize: viper.GetUint("statediff.workerQueueSize"),
+		PreRuns:         setupPreRunRanges(),
+	}
+	return pkg.NewStateDiffService(lvlDBReader, indexer, sdConf), nil
+}
+
+func setupPreRunRanges() []pkg.RangeRequest {
+	if !viper.GetBool("statediff.prerun") {
+		return nil
+	}
+	preRunParams := statediff.Params{
+		IncludeBlock:    viper.GetBool("prerun.params.includeBlock"),
+		IncludeReceipts: viper.GetBool("prerun.params.includeReceipts"),
+		IncludeTD:       viper.GetBool("prerun.params.includeTD"),
+		IncludeCode:     viper.GetBool("prerun.params.includeCode"),
+	}
+	var addrStrs []string
+	viper.UnmarshalKey("prerun.params.watchedAddresses", &addrStrs)
+	addrs := make([]common.Address, len(addrStrs))
+	for i, addrStr := range addrStrs {
+		addrs[i] = common.HexToAddress(addrStr)
+	}
+	preRunParams.WatchedAddresses = addrs
+	var rawRanges []blockRange
+	viper.UnmarshalKey("prerun.ranges", &rawRanges)
+	blockRanges := make([]pkg.RangeRequest, len(rawRanges))
+	for i, rawRange := range rawRanges {
+		blockRanges[i] = pkg.RangeRequest{
+			Start:  rawRange[0],
+			Stop:   rawRange[1],
+			Params: preRunParams,
+		}
+	}
+	if viper.IsSet("prerun.start") && viper.IsSet("prerun.stop") {
+		hardStart := viper.GetInt("prerun.start")
+		hardStop := viper.GetInt("prerun.stop")
+		blockRanges = append(blockRanges, pkg.RangeRequest{
+			Start:  uint64(hardStart),
+			Stop:   uint64(hardStop),
+			Params: preRunParams,
+		})
+	}
+
+	return blockRanges
+}
+
+// LoadConfig loads chain config from json file
+func LoadConfig(chainConfigPath string) (*params.ChainConfig, error) {
+	file, err := os.Open(chainConfigPath)
+	if err != nil {
+		log.Error("Failed to read chain config file", "error", err)
+
+		return nil, err
+	}
+	defer file.Close()
+
+	chainConfig := new(params.ChainConfig)
+	if err := json.NewDecoder(file).Decode(chainConfig); err != nil {
+		log.Error("invalid chain config file", "error", err)
+
+		return nil, err
+	}
+
+	log.Debug(fmt.Sprintf("Using chain config from '%s'. Content: %+v", chainConfigPath, chainConfig))
+
+	return chainConfig, nil
+}
+
+func instantiateLevelDBReader() (pkg.Reader, *params.ChainConfig, node.Info) {
 	// load some necessary params
-	logWithCommand.Info("Loading statediff service parameters")
+	logWithCommand.Debug("Loading statediff service parameters")
 	mode := viper.GetString("leveldb.mode")
 	path := viper.GetString("leveldb.path")
 	ancientPath := viper.GetString("leveldb.ancient")
@@ -39,17 +133,15 @@ func createStateDiffService() *sd.Service {
 
 	nodeInfo := getEthNodeInfo()
 
-	var chainConf *params.ChainConfig
-	var err error
 	chainConfigPath := viper.GetString("ethereum.chainConfig")
-	chainConf, err = LoadConfig(chainConfigPath)
+	chainConf, err := LoadConfig(chainConfigPath)
 	if err != nil {
-		logWithCommand.Fatal(err)
+		logWithCommand.Fatalf("Unable to instantiate chain config: %s", err)
 	}
 
 	// create LevelDB reader
-	logWithCommand.Info("Creating LevelDB reader")
-	readerConf := sd.LvLDBReaderConfig{
+	logWithCommand.Debug("Creating LevelDB reader")
+	readerConf := pkg.LvLDBReaderConfig{
 		TrieConfig: &trie.Config{
 			Cache:     viper.GetInt("cache.trie"),
 			Journal:   "",
@@ -62,49 +154,24 @@ func createStateDiffService() *sd.Service {
 		Url:         url,
 		DBCacheSize: viper.GetInt("cache.database"),
 	}
-	lvlDBReader, err := sd.NewLvlDBReader(readerConf)
+	reader, err := pkg.NewLvlDBReader(readerConf)
 	if err != nil {
-		logWithCommand.Fatal(err)
+		logWithCommand.Fatalf("Unable to instantiate levelDB reader: %s", err)
+	}
+	return reader, chainConf, nodeInfo
 }
 
-	// create statediff service
-	logWithCommand.Info("Setting up database")
-	conf, err := getConfig(nodeInfo)
+// report latest block info
+func reportLatestBlock(reader pkg.Reader) {
+	header, err := reader.GetLatestHeader()
 	if err != nil {
-		logWithCommand.Fatal(err)
+		logWithCommand.Fatalf("Unable to determine latest header height and hash: %s", err.Error())
 	}
-	logWithCommand.Info("Creating statediff indexer")
-	_, indexer, err := ind.NewStateDiffIndexer(context.Background(), chainConf, nodeInfo, conf)
-	if err != nil {
-		logWithCommand.Fatal(err)
+	if header.Number == nil {
+		logWithCommand.Fatal("Latest header found in levelDB has a nil block height")
 	}
-	logWithCommand.Info("Creating statediff service")
-	sdConf := sd.ServiceConfig{
-		ServiceWorkers:  viper.GetUint("statediff.serviceWorkers"),
-		TrieWorkers:     viper.GetUint("statediff.trieWorkers"),
-		WorkerQueueSize: viper.GetUint("statediff.workerQueueSize"),
-	}
-	return sd.NewStateDiffService(lvlDBReader, indexer, sdConf)
-}
-
-// LoadConfig loads chain config from json file
-func LoadConfig(chainConfigPath string) (*params.ChainConfig, error) {
-	file, err := os.Open(chainConfigPath)
-	if err != nil {
-		log.Error(fmt.Sprintf("Failed to read chain config file: %v", err))
-
-		return nil, err
-	}
-	defer file.Close()
-
-	chainConfig := new(params.ChainConfig)
-	if err := json.NewDecoder(file).Decode(chainConfig); err != nil {
-		log.Error(fmt.Sprintf("invalid chain config file: %v", err))
-
-		return nil, err
-	}
-
-	log.Info(fmt.Sprintf("Using chain config from %s file. Content %+v", chainConfigPath, chainConfig))
-
-	return chainConfig, nil
+	logWithCommand.
+		WithField("height", header.Number).
+		WithField("hash", header.Hash()).
+		Info("Latest block found in levelDB")
 }

cmd/version.go

@@ -20,7 +20,7 @@ import (
 	log "github.com/sirupsen/logrus"
 	"github.com/spf13/cobra"
 
-	v "github.com/vulcanize/eth-statediff-service/version"
+	v "github.com/cerc-io/eth-statediff-service/version"
 )
 
 // versionCmd represents the version command

docker-compose.yml

@@ -1,21 +0,0 @@
-services:
-  eth-statediff-service:
-    build:
-      context: ./
-      cache_from:
-      - alpine:latest
-      - golang:1.18
-      dockerfile: ./Dockerfile
-      args:
-        USER: "vdbm"
-        CONFIG_FILE: ./environments/docker.toml
-        EXPOSE_PORT: 8545
-    environment:
-    - VDB_COMMAND=serve
-    volumes:
-    - eth-statediff-service-data:/vdbm/.ethereum/
-    ports:
-    - "127.0.0.1:8545:8545"
-
-volumes:
-  eth-statediff-service-data:

environments/example.toml

@@ -1,59 +1,104 @@
 [leveldb]
-    mode = "local"
-    path = "/home/user/.ethereum/geth/chaindata"
-    ancient = "/home/user/.ethereum/geth/chaindata/ancient"
-    url = "http://127.0.0.1:8082/"
+    # LevelDB access mode <local | remote>
+    mode = "local"  # LEVELDB_MODE
+
+    # LevelDB paths (local mode)
+    path    = "/Users/user/Library/Ethereum/geth/chaindata"         # LEVELDB_PATH
+    ancient = "/Users/user/Library/Ethereum/geth/chaindata/ancient" # LEVELDB_ANCIENT
+
+    # URL for leveldb-ethdb-rpc endpoint (remote mode)
+    url = "http://127.0.0.1:8082/"  # LEVELDB_URL
 
 [server]
-    ipcPath = ".ipc"
-    httpPath = "127.0.0.1:8545"
+    ipcPath  = ".ipc"           # SERVICE_IPC_PATH
+    httpPath = "127.0.0.1:8545" # SERVICE_HTTP_PATH
 
 [statediff]
-    serviceWorkers = 1
-    workerQueueSize = 1024
-    trieWorkers = 4
+    prerun          = true  # STATEDIFF_PRERUN
+    serviceWorkers  = 1     # STATEDIFF_SERVICE_WORKERS
+    workerQueueSize = 1024  # STATEDIFF_WORKER_QUEUE_SIZE
+    trieWorkers     = 4     # STATEDIFF_TRIE_WORKERS
 
-[run]
+[prerun]
+    only = false     # PRERUN_ONLY
+    parallel = true  # PRERUN_PARALLEL
+
+    # to perform prerun in a specific range (optional)
+    start = 0   # PRERUN_RANGE_START
+    stop  = 100 # PRERUN_RANGE_STOP
+
+    # to perform prerun over multiple ranges (optional)
     ranges = [
-        [0, 1000]
+        [101, 1000]
     ]
-    [run.params]
-        includeBlock = true
-        includeReceipts = true
-        includeTD = true
-        includeCode = true
+
+    # statediffing params for prerun
+    [prerun.params]
+        intermediateStateNodes   = true # PRERUN_INTERMEDIATE_STATE_NODES
+        intermediateStorageNodes = true # PRERUN_INTERMEDIATE_STORAGE_NODES
+        includeBlock             = true # PRERUN_INCLUDE_BLOCK
+        includeReceipts          = true # PRERUN_INCLUDE_RECEIPTS
+        includeTD                = true # PRERUN_INCLUDE_TD
+        includeCode              = true # PRERUN_INCLUDE_CODE
         watchedAddresses         = []
 
 [log]
-    file = ""
-    level = "info"
+    # Leave empty to output to stdout
+    file  = ""      # LOG_FILE_PATH
+    level = "info"  # LOG_LEVEL
 
 [database]
-    name            = "cerc_testing"
-    hostname        = "localhost"
-    port            = 5432
-    user            = "vdbm"
-    password        = "password"
+    # output type <postgres | file | dump>
     type = "postgres"
-    driver          = "sqlx"
-    dumpDestination = ""
-    filePath        = ""
+
+    # with postgres type
+    # db credentials
+    name     = "vulcanize_test" # DATABASE_NAME
+    hostname = "localhost"      # DATABASE_HOSTNAME
+    port     = 5432             # DATABASE_PORT
+    user     = "vulcanize"      # DATABASE_USER
+    password = "..."            # DATABASE_PASSWORD
+    # SQL backend to use: <sqlx | pgx>
+    driver   = "sqlx"           # DATABASE_DRIVER_TYPE
+
+    # with file type
+    # file mode <sql | csv>
+    fileMode = "csv"    # DATABASE_FILE_MODE
+
+    # with SQL file mode
+    filePath = ""   # DATABASE_FILE_PATH
+
+    # with CSV file mode
+    fileCsvDir = "output_dir" # DATABASE_FILE_CSV_DIR
+
+    # with dump type
+    # <stdout | stderr | discard>
+    dumpDestination = ""    # DATABASE_DUMP_DST
 
 [cache]
-    database = 1024
-    trie = 1024
+    # settings for geth internal caches
+    database = 1024 # DB_CACHE_SIZE_MB
+    trie     = 1024 # TRIE_CACHE_SIZE_MB
 
 [prom]
-    dbStats = false
-    metrics = true
-    http = true
-    httpAddr = "localhost"
-    httpPort = "8889"
+    # prometheus metrics
+    metrics  = true         # PROM_METRICS
+    http     = true         # PROM_HTTP
+    httpAddr = "localhost"  # PROM_HTTP_ADDR
+    httpPort = "8889"       # PROM_HTTP_PORT
+    dbStats = true          # PROM_DB_STATS
 
 [ethereum]
-    chainConfig = ""
-    nodeID = ""
-    clientName = "eth-statediff-service"
-    genesisBlock = "0xd4e56740f876aef8c010b86a40d5f56745a118d0906a34e69aec8c0db1cb8fa3"
-    networkID = 1
-    chainID = 1
+    # Identifiers for ethereum node
+    nodeID       = ""                       # ETH_NODE_ID
+    clientName   = "eth-statediff-service"  # ETH_CLIENT_NAME
+    networkID    = 1                        # ETH_NETWORK_ID
+    chainID      = 1                        # ETH_CHAIN_ID
+    genesisBlock = "0xd4e56740f876aef8c010b86a40d5f56745a118d0906a34e69aec8c0db1cb8fa3" # ETH_GENESIS_BLOCK
+
+    # Path to custom chain config file (optional)
+    # chainID should match that in this config file
+    chainConfig  = "chain.json"           # ETH_CHAIN_CONFIG
+
+[debug]
+    pprof = false                           # DEBUG_PPROF

fixture/.gitignore

@@ -0,0 +1,6 @@
+*/*.log
+*/CURRENT*
+*/LOCK
+*/LOG
+*/MANIFEST-*
+*/ancient/FLOCK

fixture/chaindata/ancient/bodies.meta

@@ -0,0 +1 @@
+<EFBFBD>
<01>

fixture/chaindata/ancient/diffs.meta

@@ -0,0 +1 @@
+<EFBFBD>
<01>

fixture/chaindata/ancient/hashes.meta

@@ -0,0 +1 @@
+<EFBFBD>
<01>

fixture/chaindata/ancient/headers.meta

@@ -0,0 +1 @@
+<EFBFBD>
<01>

fixture/chaindata/ancient/receipts.meta

@@ -0,0 +1 @@
+<EFBFBD>
<01>

go.mod

@@ -1,16 +1,16 @@
-module github.com/vulcanize/eth-statediff-service
+module github.com/cerc-io/eth-statediff-service
 
 go 1.19
 
 require (
+	github.com/cerc-io/leveldb-ethdb-rpc v1.1.13
 	github.com/cerc-io/plugeth-statediff v0.0.0-00010101000000-000000000000
 	github.com/ethereum/go-ethereum v1.12.0
-	github.com/jmoiron/sqlx v1.2.0
+	github.com/jmoiron/sqlx v1.3.5 // indirect
 	github.com/prometheus/client_golang v1.16.0
 	github.com/sirupsen/logrus v1.9.0
 	github.com/spf13/cobra v1.3.0
 	github.com/spf13/viper v1.10.1
-	github.com/vulcanize/leveldb-ethdb-rpc v0.1.2
 )
 
 require (
@@ -112,7 +112,7 @@ require (
 	github.com/stretchr/objx v0.5.0 // indirect
 	github.com/stretchr/testify v1.8.2 // indirect
 	github.com/subosito/gotenv v1.2.0 // indirect
-	github.com/syndtr/goleveldb v1.0.1-0.20210819022825-2ae1ddf74ef7 // indirect
+	github.com/syndtr/goleveldb v1.0.1-0.20220614013038-64ee5596c38a // indirect
 	github.com/thoas/go-funk v0.9.3 // indirect
 	github.com/tklauser/go-sysconf v0.3.11 // indirect
 	github.com/tklauser/numcpus v0.6.1 // indirect
@@ -139,9 +139,9 @@ require (
 
 replace (
 	github.com/cerc-io/eth-iterator-utils => git.vdb.to/cerc-io/eth-iterator-utils v0.0.0-20230803115933-6bb6d4e27fd2
+	// github.com/cerc-io/plugeth-statediff => ../plugeth-statediff
 	// github.com/cerc-io/plugeth-statediff => git.vdb.to/cerc-io/plugeth-statediff v0.1.0
-	github.com/cerc-io/plugeth-statediff => ../plugeth-statediff
-	// github.com/ethereum/go-ethereum => git.vdb.to/cerc-io/plugeth v0.0.0-20230808125822-691dc334fab1
-	github.com/ethereum/go-ethereum => ../plugeth
+	github.com/cerc-io/plugeth-statediff => git.vdb.to/cerc-io/plugeth-statediff v0.1.1-0.20230901070823-5ed22c03d29a
+	github.com/ethereum/go-ethereum => git.vdb.to/cerc-io/plugeth v0.0.0-20230808125822-691dc334fab1
 	github.com/openrelayxyz/plugeth-utils => git.vdb.to/cerc-io/plugeth-utils v0.0.0-20230706160122-cd41de354c46
 )

go.sum

@@ -48,6 +48,10 @@ cloud.google.com/go/storage v1.10.0/go.mod h1:FLPqc6j+Ki4BU591ie1oL6qBQGu2Bl/tZ9
 dmitri.shuralyov.com/gpu/mtl v0.0.0-20190408044501-666a987793e9/go.mod h1:H6x//7gZCb22OMCxBHrMx7a5I7Hp++hsVxbQ4BYO7hU=
 git.vdb.to/cerc-io/eth-iterator-utils v0.0.0-20230803115933-6bb6d4e27fd2 h1:UImCl/qXSk9WD5hG1PLS4wfjkHIdgr+5BvzsNqeWEv4=
 git.vdb.to/cerc-io/eth-iterator-utils v0.0.0-20230803115933-6bb6d4e27fd2/go.mod h1:VtTq+MbVe5aKTtb/CoSySjz5vXPFOs9HPBTALmEUfj4=
+git.vdb.to/cerc-io/plugeth v0.0.0-20230808125822-691dc334fab1 h1:KLjxHwp9Zp7xhECccmJS00RiL+VwTuUGLU7qeIctg8g=
+git.vdb.to/cerc-io/plugeth v0.0.0-20230808125822-691dc334fab1/go.mod h1:cYXZu70+6xmDgIgrTD81GPasv16piiAFJnKyAbwVPMU=
+git.vdb.to/cerc-io/plugeth-statediff v0.1.1-0.20230901070823-5ed22c03d29a h1:/bCbcXZNqampJ86LqHr1U3QiKtys4w264q5jSFpuEBQ=
+git.vdb.to/cerc-io/plugeth-statediff v0.1.1-0.20230901070823-5ed22c03d29a/go.mod h1:1VcABflu6M2GvcBXu5nc+GrGcgR6/2AZXtOIjMZgceo=
 git.vdb.to/cerc-io/plugeth-utils v0.0.0-20230706160122-cd41de354c46 h1:KYcbbne/RXd7AuxbUd/3hgk1jPN+33k2CKiNsUsMCC0=
 git.vdb.to/cerc-io/plugeth-utils v0.0.0-20230706160122-cd41de354c46/go.mod h1:VpDN61dxy64zGff05F0adujR5enD/JEdXBkTQ+PaIsQ=
 github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
@@ -81,6 +85,8 @@ github.com/btcsuite/btcd/btcec/v2 v2.3.2/go.mod h1:zYzJ8etWJQIv1Ogk7OzpWjowwOdXY
 github.com/btcsuite/btcd/chaincfg/chainhash v1.0.1 h1:q0rUy8C/TYNBQS1+CGKw68tLOFYSNEs0TFnxxnS9+4U=
 github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
 github.com/census-instrumentation/opencensus-proto v0.3.0/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
+github.com/cerc-io/leveldb-ethdb-rpc v1.1.13 h1:XM+e/JLKjNoYc4Xj7DJNNlFI4+3HpqZ9VkVlrWBlwHg=
+github.com/cerc-io/leveldb-ethdb-rpc v1.1.13/go.mod h1:ZNa5ySrKJ0ZLsJ0nSNaQ+11PkX29Juy9+omMgP6mw1c=
 github.com/cespare/cp v0.1.0 h1:SE+dxFebS7Iik5LK0tsi1k9ZCxEaFX4AjQmoyA+1dJk=
 github.com/cespare/xxhash v1.1.0/go.mod h1:XrSqR1VqqWfGrhpAt58auRo0WTKS1nRRg3ghfAqPWnc=
 github.com/cespare/xxhash/v2 v2.1.1/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
@@ -164,6 +170,7 @@ github.com/fjl/memsize v0.0.1/go.mod h1:VvhXpOYNQvB+uIk2RvXzuaQtkQJzzIx6lSBe1xv7
 github.com/fsnotify/fsnotify v1.4.7/go.mod h1:jwhsz4b93w/PPRr/qN1Yymfu8t87LnFCMoQvtojpjFo=
 github.com/fsnotify/fsnotify v1.4.9/go.mod h1:znqG4EE+3YCdAaPaxE2ZRY/06pZUdp0tY4IgpuI1SZQ=
 github.com/fsnotify/fsnotify v1.5.1/go.mod h1:T3375wBYaZdLLcVNkcVbzGHY7f1l/uK5T5Ai1i3InKU=
+github.com/fsnotify/fsnotify v1.5.4/go.mod h1:OVB6XrOHzAwXMpEM7uPOzcehqUV2UqJxmVXmkdnm1bU=
 github.com/fsnotify/fsnotify v1.6.0 h1:n+5WquG0fcWoWp6xPWfHdbskMCQaFnG6PfBrh1Ky4HY=
 github.com/fsnotify/fsnotify v1.6.0/go.mod h1:sl3t1tCWJFWoRz9R8WJCbQihKKwmorjAbSClcnxKAGw=
 github.com/gballet/go-libpcsclite v0.0.0-20190607065134-2772fd86a8ff h1:tY80oXqGNY4FhTFhk+o9oFHGINQ/+vhlm8HFzi6znCI=
@@ -191,11 +198,13 @@ github.com/go-ole/go-ole v1.2.6/go.mod h1:pprOEPIfldk/42T2oK7lQ4v4JSDwmV0As9GaiU
 github.com/go-openapi/jsonpointer v0.19.5/go.mod h1:Pl9vOtqEWErmShwVjC8pYs9cog34VGT37dQOVbmoatg=
 github.com/go-openapi/swag v0.19.5/go.mod h1:POnQmlKehdgb5mhVOsnJFsivZCEZ/vjK9gh66Z9tfKk=
 github.com/go-sql-driver/mysql v1.4.0/go.mod h1:zAC/RDZ24gD3HViQzih4MyKcchzm+sOG5ZlKdlhCg5w=
-github.com/go-sql-driver/mysql v1.4.1 h1:g24URVg0OFbNUTx9qqY1IRZ9D9z3iPyi5zKhQZpNwpA=
 github.com/go-sql-driver/mysql v1.4.1/go.mod h1:zAC/RDZ24gD3HViQzih4MyKcchzm+sOG5ZlKdlhCg5w=
+github.com/go-sql-driver/mysql v1.6.0 h1:BCTh4TKNUYmOmMUcQ3IipzF5prigylS7XXjEkfCHuOE=
+github.com/go-sql-driver/mysql v1.6.0/go.mod h1:DCzpHaOWr8IXmIStZouvnhqoel9Qv2LBy8hT2VhHyBg=
 github.com/go-stack/stack v1.8.0/go.mod h1:v0f6uXyyMGvRgIKkXu+yp6POWl0qKG85gN/melR3HDY=
 github.com/go-stack/stack v1.8.1 h1:ntEHSVwIt7PNXNpgPmVfMrNhLtgjlmnZha2kOpuRiDw=
 github.com/go-stack/stack v1.8.1/go.mod h1:dcoOX6HbPZSZptuspn9bctJ+N/CnF5gGygcUP3XYfe4=
+github.com/go-task/slim-sprig v0.0.0-20210107165309-348f09dbbbc0/go.mod h1:fyg7847qk6SyHyPtNmDHnmrv/HOrqktSC+C9fM+CJOE=
 github.com/godbus/dbus/v5 v5.0.4/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
 github.com/gofrs/flock v0.8.1 h1:+gYjHKf32LDeiEEFhQaotPbLuUXjY5ZqxKgXy7n59aw=
 github.com/gofrs/flock v0.8.1/go.mod h1:F1TvTiK9OcQqauNUHlbJvyl9Qa1QvF/gOUDKA14jxHU=
@@ -278,6 +287,7 @@ github.com/google/pprof v0.0.0-20201023163331-3e6fc7fc9c4c/go.mod h1:kpwsk12EmLe
 github.com/google/pprof v0.0.0-20201203190320-1bf35d6f28c2/go.mod h1:kpwsk12EmLew5upagYY7GY0pfYCcupk39gWOCRROcvE=
 github.com/google/pprof v0.0.0-20210122040257-d980be63207e/go.mod h1:kpwsk12EmLew5upagYY7GY0pfYCcupk39gWOCRROcvE=
 github.com/google/pprof v0.0.0-20210226084205-cbba55b83ad5/go.mod h1:kpwsk12EmLew5upagYY7GY0pfYCcupk39gWOCRROcvE=
+github.com/google/pprof v0.0.0-20210407192527-94a9f03dee38/go.mod h1:kpwsk12EmLew5upagYY7GY0pfYCcupk39gWOCRROcvE=
 github.com/google/pprof v0.0.0-20210601050228-01bbb1931b22/go.mod h1:kpwsk12EmLew5upagYY7GY0pfYCcupk39gWOCRROcvE=
 github.com/google/pprof v0.0.0-20210609004039-a478d1d731e9/go.mod h1:kpwsk12EmLew5upagYY7GY0pfYCcupk39gWOCRROcvE=
 github.com/google/pprof v0.0.0-20210720184732-4bb14d4b1be1/go.mod h1:kpwsk12EmLew5upagYY7GY0pfYCcupk39gWOCRROcvE=
@@ -425,8 +435,9 @@ github.com/jackpal/go-nat-pmp v1.0.2/go.mod h1:QPH045xvCAeXUZOxsnwmrtiCoxIr9eob+
 github.com/jinzhu/gorm v1.9.12/go.mod h1:vhTjlKSJUTWNtcbQtrMBFCxy7eXTzeCAzfL5fBZT/Qs=
 github.com/jinzhu/inflection v1.0.0/go.mod h1:h+uFLlag+Qp1Va5pdKtLDYj+kHp5pxUVkryuEj+Srlc=
 github.com/jinzhu/now v1.0.1/go.mod h1:d3SSVoowX0Lcu0IBviAWJpolVfI5UJVZZ7cO71lE/z8=
-github.com/jmoiron/sqlx v1.2.0 h1:41Ip0zITnmWNR/vHV+S4m+VoUivnWY5E4OJfLZjCJMA=
 github.com/jmoiron/sqlx v1.2.0/go.mod h1:1FEQNm3xlJgrMD+FBdI9+xvCksHtbpVBBw5dYhBSsks=
+github.com/jmoiron/sqlx v1.3.5 h1:vFFPA71p1o5gAeqtEAwLU4dnX2napprKtHr7PYIcN3g=
+github.com/jmoiron/sqlx v1.3.5/go.mod h1:nRVWtLre0KfCLJvgxzCsLVMogSvQ1zNJtpYr2Ccp0mQ=
 github.com/json-iterator/go v1.1.6/go.mod h1:+SdeFBvtyEkXs7REEP0seUULqWtbJapLOCVDaaPEHmU=
 github.com/json-iterator/go v1.1.9/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
 github.com/json-iterator/go v1.1.11/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
@@ -500,6 +511,7 @@ github.com/mattn/go-runewidth v0.0.9/go.mod h1:H031xJmbD/WCDINGzjvQ9THkh0rPKHF+m
 github.com/mattn/go-runewidth v0.0.14 h1:+xnbZSEeDbOIg5/mE6JF0w6n9duR1l3/WmbinWVwUuU=
 github.com/mattn/go-runewidth v0.0.14/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w=
 github.com/mattn/go-sqlite3 v1.9.0/go.mod h1:FPy6KqzDD04eiIsT53CuJW3U88zkxoIYsOqkbpncsNc=
+github.com/mattn/go-sqlite3 v1.14.6/go.mod h1:NyWgC/yNuGj7Q9rpYnZvas74GogHl5/Z4A/KQRfk6bU=
 github.com/mattn/go-sqlite3 v2.0.1+incompatible h1:xQ15muvnzGBHpIpdrNi1DA5x0+TcBZzsIDwmw9uTHzw=
 github.com/mattn/go-sqlite3 v2.0.1+incompatible/go.mod h1:FPy6KqzDD04eiIsT53CuJW3U88zkxoIYsOqkbpncsNc=
 github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
@@ -539,17 +551,22 @@ github.com/multiformats/go-multihash v0.2.3/go.mod h1:dXgKXCXjBzdscBLk9JkjINiEsC
 github.com/multiformats/go-varint v0.0.7 h1:sWSGR+f/eu5ABZA2ZpYKBILXTTs9JWpdEM/nEGOHFS8=
 github.com/multiformats/go-varint v0.0.7/go.mod h1:r8PUYw/fD/SjBCiKOoDlGF6QawOELpZAu9eioSos/OU=
 github.com/mwitkow/go-conntrack v0.0.0-20161129095857-cc309e4a2223/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U=
-github.com/nxadm/tail v1.4.4 h1:DQuhQpB1tVlglWS2hLQ5OV6B5r8aGxSrPc5Qo6uTN78=
 github.com/nxadm/tail v1.4.4/go.mod h1:kenIhsEOeOJmVchQTgglprH7qJGnHDVpk1VPCcaMI8A=
+github.com/nxadm/tail v1.4.8 h1:nPr65rt6Y5JFSKQO7qToXr7pePgD6Gwiw05lkbyAQTE=
+github.com/nxadm/tail v1.4.8/go.mod h1:+ncqLTQzXmGhMZNUePPaPqPvBxHAIsmXswZKocGu+AU=
 github.com/olekukonko/tablewriter v0.0.5 h1:P2Ga83D34wi1o9J6Wh1mRuqd4mF/x/lgBS7N7AbDhec=
 github.com/olekukonko/tablewriter v0.0.5/go.mod h1:hPp6KlRPjbx+hW8ykQs1w3UBbZlj6HuIJcUGPhkA7kY=
 github.com/onsi/ginkgo v1.6.0/go.mod h1:lLunBs/Ym6LB5Z9jYTR76FiuTmxDTDusOGeTQH+WWjE=
 github.com/onsi/ginkgo v1.12.1/go.mod h1:zj2OWP4+oCPe1qIXoGWkgMRwljMUYCdkwsT2108oapk=
-github.com/onsi/ginkgo v1.14.0/go.mod h1:iSB4RoI2tjJc9BBv4NKIKWKya62Rps+oPG/Lv9klQyY=
+github.com/onsi/ginkgo v1.16.4/go.mod h1:dX+/inL/fNMqNlz0e9LfyB9TswhZpCVdJM/Z6Vvnwo0=
 github.com/onsi/ginkgo v1.16.5 h1:8xi0RTUf59SOSfEtZMvwTvXYMzG4gV23XVHOZiXNtnE=
+github.com/onsi/ginkgo v1.16.5/go.mod h1:+E8gABHa3K6zRBolWtd+ROzc/U5bkGt0FwiG042wbpU=
+github.com/onsi/ginkgo/v2 v2.1.3/go.mod h1:vw5CSIxN1JObi/U8gcbwft7ZxR2dgaR70JSE3/PpL4c=
 github.com/onsi/gomega v1.7.1/go.mod h1:XdKZgCCFLUoM/7CFJVPcG8C1xQ1AJ0vpAezJrB7JYyY=
 github.com/onsi/gomega v1.10.1/go.mod h1:iN09h71vgCQne3DLsj+A5owkum+a2tYe+TOCB1ybHNo=
-github.com/onsi/gomega v1.13.0 h1:7lLHu94wT9Ij0o6EWWclhu0aOh32VxhkwEJvzuWPeak=
+github.com/onsi/gomega v1.17.0/go.mod h1:HnhC7FXeEQY45zxNK3PPoIUhzk/80Xly9PcubAlGdZY=
+github.com/onsi/gomega v1.19.0 h1:4ieX6qQjPP/BfC3mpsAtIGGlxTWPeA3Inl/7DtXw1tw=
+github.com/onsi/gomega v1.19.0/go.mod h1:LY+I3pBVzYsTBU1AnDwOSxaYi9WoWiqgwooUqq9yPro=
 github.com/opentracing/opentracing-go v1.1.0/go.mod h1:UkNAQd3GIcIGf0SeVgPpRdFStlNbqXla1AfSYxPUl2o=
 github.com/opentracing/opentracing-go v1.2.0 h1:uEJPy/1a5RIPAJ0Ov+OIO8OxWu77jEv+1B0VhjKrZUs=
 github.com/opentracing/opentracing-go v1.2.0/go.mod h1:GxEUsuufX4nBwe+T+Wl9TAgYrxe9dPLANfrWvHYVTgc=
@@ -655,13 +672,14 @@ github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5
 github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/stretchr/testify v1.7.2/go.mod h1:R6va5+xMeoiuVRoj+gSkQ7d3FALtqAAGI1FQKckRals=
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
 github.com/stretchr/testify v1.8.2 h1:+h33VjcLVPDHtOdpUCuF+7gSuG3yGIftsP1YvFihtJ8=
 github.com/stretchr/testify v1.8.2/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
 github.com/subosito/gotenv v1.2.0 h1:Slr1R9HxAlEKefgq5jn9U+DnETlIUa6HfgEzj0g5d7s=
 github.com/subosito/gotenv v1.2.0/go.mod h1:N0PQaV/YGNqwC0u51sEeR/aUtSLEXKX9iv69rRypqCw=
-github.com/syndtr/goleveldb v1.0.1-0.20210819022825-2ae1ddf74ef7 h1:epCh84lMvA70Z7CTTCmYQn2CKbY8j86K7/FAIr141uY=
-github.com/syndtr/goleveldb v1.0.1-0.20210819022825-2ae1ddf74ef7/go.mod h1:q4W45IWZaF22tdD+VEXcAWRA037jwmWEB5VWYORlTpc=
+github.com/syndtr/goleveldb v1.0.1-0.20220614013038-64ee5596c38a h1:1ur3QoCqvE5fl+nylMaIr9PVV1w343YRDtsy+Rwu7XI=
+github.com/syndtr/goleveldb v1.0.1-0.20220614013038-64ee5596c38a/go.mod h1:RRCYJbIwD5jmqPI9XoAFR0OcDxqUctll6zUj/+B4S48=
 github.com/thoas/go-funk v0.9.3 h1:7+nAEx3kn5ZJcnDm2Bh23N2yOtweO14bi//dvRtgLpw=
 github.com/thoas/go-funk v0.9.3/go.mod h1:+IWnUfUmFO1+WVYQWQtIJHeRRdaIyyYglZN7xzUPe4Q=
 github.com/tklauser/go-sysconf v0.3.11 h1:89WgdJhk5SNwJfu+GKyYveZ4IaJ7xAkecBo+KdJV0CM=
@@ -677,8 +695,6 @@ github.com/urfave/cli/v2 v2.25.7/go.mod h1:8qnjx1vcq5s2/wpsqoZFndg2CE5tNFyrTvS6S
 github.com/valyala/bytebufferpool v1.0.0/go.mod h1:6bBcMArwyJ5K/AmCkWv1jt77kVWyCJ6HpOuEn7z0Csc=
 github.com/valyala/fasttemplate v1.0.1/go.mod h1:UQGH1tvbgY+Nz5t2n7tXsz52dQxojPUpymEIMZ47gx8=
 github.com/valyala/fasttemplate v1.2.1/go.mod h1:KHLXt3tVN2HBp8eijSv/kGJopbvo7S+qRAEEKiv+SiQ=
-github.com/vulcanize/leveldb-ethdb-rpc v0.1.2 h1:ws/CsvxsPQh6IOQGsUDCPaNuPzcDjtVW1sT8o20Nfg4=
-github.com/vulcanize/leveldb-ethdb-rpc v0.1.2/go.mod h1:lksnBYanEe9GuDDeYMtpbc0JnPy4mOKImw4M8vkqJDw=
 github.com/xrash/smetrics v0.0.0-20201216005158-039620a65673 h1:bAn7/zixMGCfxrRTfdpNzjtPYqr8smhKouy9mxVdGPU=
 github.com/xrash/smetrics v0.0.0-20201216005158-039620a65673/go.mod h1:N3UwUGtsrSj3ccvlPHLoLsHnpR27oXr4ZE984MbSER8=
 github.com/yuin/goldmark v1.1.25/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
@@ -806,7 +822,6 @@ golang.org/x/net v0.0.0-20200520004742-59133d7f0dd7/go.mod h1:qpuaurCH72eLCgpAm/
 golang.org/x/net v0.0.0-20200520182314-0ba52f642ac2/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
 golang.org/x/net v0.0.0-20200625001655-4c5254603344/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
 golang.org/x/net v0.0.0-20200707034311-ab3426394381/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
-golang.org/x/net v0.0.0-20200813134508-3edf25e44fcc/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
 golang.org/x/net v0.0.0-20200822124328-c89045814202/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
 golang.org/x/net v0.0.0-20201021035429-f5854403a974/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
 golang.org/x/net v0.0.0-20201031054903-ff519b6c9102/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
@@ -817,8 +832,11 @@ golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v
 golang.org/x/net v0.0.0-20210316092652-d523dce5a7f4/go.mod h1:RBQZq4jEuRlivfhVLdyRGr576XBO4/greRjx4P4O3yc=
 golang.org/x/net v0.0.0-20210405180319-a5a99cb37ef4/go.mod h1:p54w0d4576C0XHj96bSt6lcn1PtDYWL6XObtHCRCNQM=
 golang.org/x/net v0.0.0-20210410081132-afb366fc7cd1/go.mod h1:9tjilg8BloeKEkVJvy7fQ90B1CfIiPueXVOjqfkSzI8=
+golang.org/x/net v0.0.0-20210428140749-89ef3d95e781/go.mod h1:OJAsFXCWl8Ukc7SiCT/9KSuxbyM7479/AVlXFRxuMCk=
 golang.org/x/net v0.0.0-20210503060351-7fd8e65b6420/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/net v0.0.0-20210813160813-60bc85c4be6d/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
+golang.org/x/net v0.0.0-20220225172249-27dd8689420f/go.mod h1:CfG3xpIq0wQ8r1q4Su4UZFWDARRcnwPjda9FqA0JpMk=
+golang.org/x/net v0.0.0-20220607020251-c690dde0001d/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
 golang.org/x/net v0.10.0 h1:X2//UzNDwYmtCLn7To6G58Wr6f5ahEAQgKNzv9Y951M=
 golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
@@ -894,16 +912,15 @@ golang.org/x/sys v0.0.0-20200331124033-c3d80250170d/go.mod h1:h1NjWce9XRLGQEsW7w
 golang.org/x/sys v0.0.0-20200501052902-10377860bb8e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200511232937-7e40ca221e25/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200515095857-1151b9dac4a9/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200519105757-fe76b779f299/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200523222454-059865788121/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200803210538-64077c9b5642/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200814200057-3d37ad5750ed/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200826173525-f9321e4c35a6/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200905004654-be1d3432aa8f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20201201145000-ef89a241ccb3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210104204734-6f8348627aad/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210112080510-489259a85091/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210119212857-b64e53b001e4/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210220050731-9a76102bfb43/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -928,6 +945,9 @@ golang.org/x/sys v0.0.0-20210927094055-39ccf1dd6fa6/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.0.0-20211007075335-d3039528d8ac/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20211124211545-fe61309f8881/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20211205182925-97ca703d548d/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20211216021012-1d35b9e2eb4e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220412211240-33da011f77ad/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220908164124-27713097b956/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
@@ -939,6 +959,7 @@ golang.org/x/sys v0.10.0 h1:SqMFp9UcQJZa+pmYuAKjd9xq1f0j5rLcDIk0mj4qAsA=
 golang.org/x/sys v0.10.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/term v0.0.0-20201117132131-f5c789dd3221/go.mod h1:Nr5EML6q2oocZ2LXRh80K7BxOlk5/8JxuGnuhpl+muw=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
+golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
 golang.org/x/term v0.10.0 h1:3R7pNqamzBraeqj/Tj8qt1aQ2HpmlC+Cx/qL/7hn4/c=
 golang.org/x/term v0.10.0/go.mod h1:lpqdcUyK/oCiQxvxVrppt5ggO2KCZ5QblwqPnfZ6d5o=
 golang.org/x/text v0.0.0-20170915032832-14c0d48ead0c/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
@@ -1010,6 +1031,7 @@ golang.org/x/tools v0.0.0-20200904185747-39188db58858/go.mod h1:Cj7w3i3Rnn0Xh82u
 golang.org/x/tools v0.0.0-20201110124207-079ba7bd75cd/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.0.0-20201201161351-ac6f37ff4c2a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.0.0-20201208233053-a543418bbed2/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
+golang.org/x/tools v0.0.0-20201224043029-2b0845dc783e/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.0.0-20210105154028-b0ab187a4818/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.0.0-20210106214847-113979e3529a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.1.0/go.mod h1:xkSsbof2nBLbhDlRMhhhyNLN/zl3eTqcnHD5viDpcZ0=
@@ -1024,6 +1046,7 @@ golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8T
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+golang.org/x/xerrors v0.0.0-20220517211312-f3a8303e98df/go.mod h1:K8+ghG5WaK9qNqU5K3HdILfMLy1f3aNYFI/wnl100a8=
 google.golang.org/api v0.4.0/go.mod h1:8k5glujaEP+g9n7WNsDg8QP6cUVNI86fCNMcbazEtwE=
 google.golang.org/api v0.7.0/go.mod h1:WtwebWUNSVBH/HAw79HIFXZNqEvBhG+Ra+ax0hx3E3M=
 google.golang.org/api v0.8.0/go.mod h1:o4eAsZoiT+ibD93RtjEohWalFOjRDx6CVaqeizhEnKg=
@@ -1062,7 +1085,6 @@ google.golang.org/appengine v1.5.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7
 google.golang.org/appengine v1.6.1/go.mod h1:i06prIuMbXzDqacNJfV5OdTW448YApPu5ww/cMBSeb0=
 google.golang.org/appengine v1.6.5/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc=
 google.golang.org/appengine v1.6.6/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc=
-google.golang.org/appengine v1.6.7 h1:FZR1q0exgwxzPzp/aF+VccGrSfxfPpkBqjIIEq3ru6c=
 google.golang.org/appengine v1.6.7/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc=
 google.golang.org/genproto v0.0.0-20180817151627-c66870c02cf8/go.mod h1:JiN7NxoALGmiZfu7CAH4rXhgtRTLTxftemlI0sWmxmc=
 google.golang.org/genproto v0.0.0-20190307195333-5fe7a883aa19/go.mod h1:VzzqZJRnGkLBvHegQrXjBqPurQTc5/KpmUdxsrq26oE=

main.go

@@ -15,7 +15,7 @@
 
 package main
 
-import "github.com/vulcanize/eth-statediff-service/cmd"
+import "github.com/cerc-io/eth-statediff-service/cmd"
 
 func main() {
 	cmd.Execute()

pkg/config.go

@@ -5,4 +5,5 @@ type ServiceConfig struct {
 	ServiceWorkers  uint
 	TrieWorkers     uint
 	WorkerQueueSize uint
+	PreRuns         []RangeRequest
 }

pkg/prom/db_stats_collector.go

@@ -17,9 +17,9 @@
 package prom
 
 import (
-	"database/sql"
-
 	"github.com/prometheus/client_golang/prometheus"
+
+	dbmetrics "github.com/cerc-io/plugeth-statediff/indexer/database/metrics"
 )
 
 const (
@@ -29,7 +29,7 @@ const (
 
 // DBStatsGetter is an interface that gets sql.DBStats.
 type DBStatsGetter interface {
-	Stats() sql.DBStats
+	Stats() dbmetrics.DbStats
 }
 
 // DBStatsCollector implements the prometheus.Collector interface.
@@ -122,41 +122,41 @@ func (c DBStatsCollector) Collect(ch chan<- prometheus.Metric) {
 	ch <- prometheus.MustNewConstMetric(
 		c.maxOpenDesc,
 		prometheus.GaugeValue,
-		float64(stats.MaxOpenConnections),
+		float64(stats.MaxOpen()),
 	)
 	ch <- prometheus.MustNewConstMetric(
 		c.openDesc,
 		prometheus.GaugeValue,
-		float64(stats.OpenConnections),
+		float64(stats.Open()),
 	)
 	ch <- prometheus.MustNewConstMetric(
 		c.inUseDesc,
 		prometheus.GaugeValue,
-		float64(stats.InUse),
+		float64(stats.InUse()),
 	)
 	ch <- prometheus.MustNewConstMetric(
 		c.idleDesc,
 		prometheus.GaugeValue,
-		float64(stats.Idle),
+		float64(stats.Idle()),
 	)
 	ch <- prometheus.MustNewConstMetric(
 		c.waitedForDesc,
 		prometheus.CounterValue,
-		float64(stats.WaitCount),
+		float64(stats.WaitCount()),
 	)
 	ch <- prometheus.MustNewConstMetric(
 		c.blockedSecondsDesc,
 		prometheus.CounterValue,
-		stats.WaitDuration.Seconds(),
+		stats.WaitDuration().Seconds(),
 	)
 	ch <- prometheus.MustNewConstMetric(
 		c.closedMaxIdleDesc,
 		prometheus.CounterValue,
-		float64(stats.MaxIdleClosed),
+		float64(stats.MaxIdleClosed()),
 	)
 	ch <- prometheus.MustNewConstMetric(
 		c.closedMaxLifetimeDesc,
 		prometheus.CounterValue,
-		float64(stats.MaxLifetimeClosed),
+		float64(stats.MaxLifetimeClosed()),
 	)
 }

pkg/prom/prom.go

@@ -19,7 +19,6 @@ package prom
 import (
 	"time"
 
-	"github.com/jmoiron/sqlx"
 	"github.com/prometheus/client_golang/prometheus"
 	"github.com/prometheus/client_golang/prometheus/promauto"
 )
@@ -123,7 +122,7 @@ func Init() {
 }
 
 // RegisterDBCollector create metric collector for given connection
-func RegisterDBCollector(name string, db *sqlx.DB) {
+func RegisterDBCollector(name string, db DBStatsGetter) {
 	if metrics {
 		prometheus.Register(NewDBStatsCollector(name, db))
 	}

pkg/reader.go

@@ -16,9 +16,11 @@
 package statediff
 
 import (
+	"errors"
 	"fmt"
 	"math/big"
 
+	"github.com/cerc-io/leveldb-ethdb-rpc/pkg/client"
 	"github.com/ethereum/go-ethereum/common"
 	"github.com/ethereum/go-ethereum/core/rawdb"
 	"github.com/ethereum/go-ethereum/core/state"
@@ -26,7 +28,6 @@ import (
 	"github.com/ethereum/go-ethereum/ethdb"
 	"github.com/ethereum/go-ethereum/params"
 	"github.com/ethereum/go-ethereum/trie"
-	"github.com/vulcanize/leveldb-ethdb-rpc/pkg/client"
 )
 
 // Reader interface required by the statediffing service
@@ -36,6 +37,7 @@ type Reader interface {
 	GetReceiptsByHash(hash common.Hash) (types.Receipts, error)
 	GetTdByHash(hash common.Hash) (*big.Int, error)
 	StateDB() state.Database
+	GetLatestHeader() (*types.Header, error)
 }
 
 // LvlDBReader exposes the necessary Reader methods on lvldb
@@ -136,3 +138,12 @@ func (ldr *LvlDBReader) GetTdByHash(hash common.Hash) (*big.Int, error) {
 func (ldr *LvlDBReader) StateDB() state.Database {
 	return ldr.stateDB
 }
+
+// GetLatestHeader gets the latest header from the levelDB
+func (ldr *LvlDBReader) GetLatestHeader() (*types.Header, error) {
+	header := rawdb.ReadHeadHeader(ldr.ethDB)
+	if header == nil {
+		return nil, errors.New("unable to read head header")
+	}
+	return header, nil
+}

pkg/rpc/http.go

@@ -24,7 +24,7 @@ import (
 	"github.com/ethereum/go-ethereum/rpc"
 	log "github.com/sirupsen/logrus"
 
-	"github.com/vulcanize/eth-statediff-service/pkg/prom"
+	"github.com/cerc-io/eth-statediff-service/pkg/prom"
 )
 
 // StartHTTPEndpoint starts the HTTP RPC endpoint, configured with cors/vhosts/modules.

pkg/rpc/ipc.go

@@ -26,7 +26,7 @@ import (
 	"github.com/ethereum/go-ethereum/rpc"
 	log "github.com/sirupsen/logrus"
 
-	"github.com/vulcanize/eth-statediff-service/pkg/prom"
+	"github.com/cerc-io/eth-statediff-service/pkg/prom"
 )
 
 var (
@@ -79,7 +79,7 @@ func StartIPCEndpoint(ipcEndpoint string, apis []rpc.API) (net.Listener, *rpc.Se
 		if err := handler.RegisterName(api.Namespace, api.Service); err != nil {
 			return nil, nil, err
 		}
-		log.Debug("IPC registered", "namespace", api.Namespace)
+		log.WithField("namespace", api.Namespace).Debug("IPC server registered")
 	}
 	// All APIs registered, start the IPC listener.
 	listener, err := ipcListen(ipcEndpoint)

pkg/service.go

@@ -33,7 +33,7 @@ import (
 	"github.com/ethereum/go-ethereum/rpc"
 	"github.com/sirupsen/logrus"
 
-	"github.com/vulcanize/eth-statediff-service/pkg/prom"
+	"github.com/cerc-io/eth-statediff-service/pkg/prom"
 )
 
 const defaultQueueSize = 1024
@@ -52,14 +52,14 @@ type Service struct {
 	queue chan RangeRequest
 	// number of ranges we can work over concurrently
 	workers uint
+	// ranges configured locally
+	preruns []RangeRequest
 }
 
 // NewStateDiffService creates a new Service
 func NewStateDiffService(lvlDBReader Reader, indexer interfaces.StateDiffIndexer, conf ServiceConfig) *Service {
-	builder := statediff.NewBuilderWithOptions(
-		adapt.GethStateView(lvlDBReader.StateDB()),
-		statediff.BuilderOptions{SubtrieWorkers: conf.TrieWorkers},
-	)
+	builder := statediff.NewBuilder(adapt.GethStateView(lvlDBReader.StateDB()))
+	builder.SetSubtrieWorkers(conf.TrieWorkers)
 	if conf.WorkerQueueSize == 0 {
 		conf.WorkerQueueSize = defaultQueueSize
 	}
@@ -69,6 +69,7 @@ func NewStateDiffService(lvlDBReader Reader, indexer interfaces.StateDiffIndexer
 		indexer:     indexer,
 		workers:     conf.ServiceWorkers,
 		queue:       make(chan RangeRequest, conf.WorkerQueueSize),
+		preruns:     conf.PreRuns,
 	}
 }
 
@@ -89,9 +90,82 @@ func (sds *Service) APIs() []rpc.API {
 	}
 }
 
+func segmentRange(workers, start, stop uint64, params statediff.Params) []RangeRequest {
+	segmentSize := ((stop - start) + 1) / workers
+	remainder := ((stop - start) + 1) % workers
+	numOfSegments := workers
+	if remainder > 0 {
+		numOfSegments++
+	}
+	segments := make([]RangeRequest, numOfSegments)
+	for i := range segments {
+		end := start + segmentSize - 1
+		if end > stop {
+			end = stop
+		}
+		segments[i] = RangeRequest{start, end, params}
+		start = end + 1
+	}
+	return segments
+}
+
 // Run does a one-off processing run on the provided RangeRequests + any pre-runs, exiting afterwards
-func (sds *Service) Run(rngs []RangeRequest) error {
+func (sds *Service) Run(rngs []RangeRequest, parallel bool) error {
+	for _, preRun := range sds.preruns {
+		// if the rangeSize is smaller than the number of workers
+		// make sure we do synchronous processing to avoid quantization issues
+		rangeSize := (preRun.Stop - preRun.Start) + 1
+		numWorkers := uint64(sds.workers)
+		if rangeSize < numWorkers {
+			parallel = false
+		}
+		if parallel {
+			logrus.Infof("parallel processing prerun range (%d, %d) (%d blocks) divided into %d sized chunks with %d workers", preRun.Start, preRun.Stop,
+				rangeSize, rangeSize/numWorkers, numWorkers)
+			workChan := make(chan RangeRequest)
+			quitChan := make(chan struct{})
+			// spin up numWorkers number of worker goroutines
+			wg := new(sync.WaitGroup)
+			for i := 0; i < int(numWorkers); i++ {
+				wg.Add(1)
+				go func(id int) {
+					defer wg.Done()
+					for {
+						select {
+						case workerSegment := <-workChan:
+							for j := workerSegment.Start; j <= workerSegment.Stop; j++ {
+								if err := sds.WriteStateDiffAt(j, workerSegment.Params); err != nil {
+									logrus.Errorf("error writing statediff at height %d in range (%d, %d) : %v", id, workerSegment.Start, workerSegment.Stop, err)
+								}
+							}
+							logrus.Infof("prerun worker %d finished processing range (%d, %d)", id, workerSegment.Start, workerSegment.Stop)
+						case <-quitChan:
+							return
+						}
+					}
+				}(i)
+			}
+			// break range up into segments
+			segments := segmentRange(numWorkers, preRun.Start, preRun.Stop, preRun.Params)
+			// send the segments to the work channel
+			for _, segment := range segments {
+				workChan <- segment
+			}
+			close(quitChan)
+			wg.Wait()
+		} else {
+			logrus.Infof("sequential processing prerun range (%d, %d)", preRun.Start, preRun.Stop)
+			for i := preRun.Start; i <= preRun.Stop; i++ {
+				if err := sds.WriteStateDiffAt(i, preRun.Params); err != nil {
+					return fmt.Errorf("error writing statediff at height %d in range (%d, %d) : %v", i, preRun.Start, preRun.Stop, err)
+				}
+			}
+		}
+	}
+	sds.preruns = nil
+	// At present this code is never called so we have not written the parallel version:
 	for _, rng := range rngs {
+		logrus.Infof("processing requested range (%d, %d)", rng.Start, rng.Stop)
 		for i := rng.Start; i <= rng.Stop; i++ {
 			if err := sds.WriteStateDiffAt(i, rng.Params); err != nil {
 				return fmt.Errorf("error writing statediff at height %d in range (%d, %d) : %v", i, rng.Start, rng.Stop, err)
@@ -115,30 +189,35 @@ func (sds *Service) Loop(wg *sync.WaitGroup) error {
 			for {
 				select {
 				case blockRange := <-sds.queue:
-					logrus.Infof("service worker %d received range (%d, %d) off of work queue, beginning processing", id, blockRange.Start, blockRange.Stop)
+					log := logrus.WithField("range", blockRange).WithField("worker", id)
+					log.Debug("processing range")
 					prom.DecQueuedRanges()
 					for j := blockRange.Start; j <= blockRange.Stop; j++ {
 						if err := sds.WriteStateDiffAt(j, blockRange.Params); err != nil {
-							logrus.Errorf("service worker %d error writing statediff at height %d in range (%d, %d) : %v", id, j, blockRange.Start, blockRange.Stop, err)
+							log.Errorf("error writing statediff at block %d: %v", j, err)
 						}
 						select {
 						case <-sds.quitChan:
-							logrus.Infof("closing service worker %d\n"+
-								"working in range (%d, %d)\n"+
-								"last processed height: %d", id, blockRange.Start, blockRange.Stop, j)
+							log.Infof("closing service worker (last processed block: %d)", j)
 							return
 						default:
-							logrus.Infof("service worker %d finished processing statediff height %d in range (%d, %d)", id, j, blockRange.Start, blockRange.Stop)
+							log.Infof("Finished processing block %d", j)
 						}
 					}
-					logrus.Infof("service worker %d finished processing range (%d, %d)", id, blockRange.Start, blockRange.Stop)
+					log.Debugf("Finished processing range")
 				case <-sds.quitChan:
-					logrus.Infof("closing the statediff service loop worker %d", id)
+					logrus.Debugf("closing the statediff service loop worker %d", id)
 					return
 				}
 			}
 		}(i)
 	}
+	for _, preRun := range sds.preruns {
+		if err := sds.WriteStateDiffsInRange(preRun.Start, preRun.Stop, preRun.Params); err != nil {
+			close(sds.quitChan)
+			return err
+		}
+	}
 	return nil
 }
 
@@ -151,7 +230,7 @@ func (sds *Service) StateDiffAt(blockNumber uint64, params statediff.Params) (*s
 	}
 	logrus.Infof("sending state diff at block %d", blockNumber)
 
-	// compute leaf keys of watched addresses in the params
+	// compute leaf paths of watched addresses in the params
 	params.ComputeWatchedAddressesLeafPaths()
 
 	if blockNumber == 0 {
@@ -171,9 +250,9 @@ func (sds *Service) StateDiffFor(blockHash common.Hash, params statediff.Params)
 	if err != nil {
 		return nil, err
 	}
-	logrus.Infof("sending state diff at block %s", blockHash.Hex())
+	logrus.Infof("sending state diff at block %s", blockHash)
 
-	// compute leaf keys of watched addresses in the params
+	// compute leaf paths of watched addresses in the params
 	params.ComputeWatchedAddressesLeafPaths()
 
 	if currentBlock.NumberU64() == 0 {
@@ -261,7 +340,7 @@ func (sds *Service) WriteStateDiffAt(blockNumber uint64, params statediff.Params
 		return err
 	}
 
-	// compute leaf keys of watched addresses in the params
+	// compute leaf paths of watched addresses in the params
 	params.ComputeWatchedAddressesLeafPaths()
 
 	parentRoot := common.Hash{}
@@ -279,14 +358,14 @@ func (sds *Service) WriteStateDiffAt(blockNumber uint64, params statediff.Params
 // This operation cannot be performed back past the point of db pruning; it requires an archival node
 // for historical data
 func (sds *Service) WriteStateDiffFor(blockHash common.Hash, params statediff.Params) error {
-	logrus.Infof("Writing state diff for block %s", blockHash.Hex())
+	logrus.Infof("Writing state diff for block %s", blockHash)
 	t := time.Now()
 	currentBlock, err := sds.lvlDBReader.GetBlockByHash(blockHash)
 	if err != nil {
 		return err
 	}
 
-	// compute leaf keys of watched addresses in the params
+	// compute leaf paths of watched addresses in the params
 	params.ComputeWatchedAddressesLeafPaths()
 
 	parentRoot := common.Hash{}
@@ -357,7 +436,7 @@ func (sds *Service) WriteStateDiffsInRange(start, stop uint64, params statediff.
 	select {
 	case sds.queue <- RangeRequest{Start: start, Stop: stop, Params: params}:
 		prom.IncQueuedRanges()
-		logrus.Infof("added range (%d, %d) to the worker queue", start, stop)
+		logrus.Infof("Added range (%d, %d) to the worker queue", start, stop)
 		return nil
 	case <-blocked.C:
 		return fmt.Errorf("unable to add range (%d, %d) to the worker queue", start, stop)

pkg/types.go

@@ -20,6 +20,8 @@
 package statediff
 
 import (
+	"fmt"
+
 	sd "github.com/cerc-io/plugeth-statediff"
 )
 
@@ -28,3 +30,7 @@ type RangeRequest struct {
 	Start, Stop uint64
 	Params      sd.Params
 }
+
+func (r RangeRequest) String() string {
+	return fmt.Sprintf("[%d,%d]", r.Start, r.Stop)
+}

scripts/.env.example

@@ -0,0 +1,28 @@
+# Used by the script to count rows (count-lines.sh)
+COUNT_LINES_LOG=./count-lines.log
+COUNT_LINES_INPUT_DIR=~/eth-statediff-service/output_dir
+COUNT_LINES_OUTPUT_FILE=./output-stats.txt
+
+# Used by the script to dedup output files (dedup.sh)
+DEDUP_LOG=./dedup.log
+DEDUP_INPUT_DIR=~/eth-statediff-service/output_dir
+DEDUP_OUTPUT_DIR=~/eth-statediff-service/dedup_dir
+DEDUP_SORT_DIR=./.sort
+
+# Used by the script to perform column checks (check-columns.sh)
+CHECK_COLUMNS_LOG=./check-columns.log
+CHECK_COLUMNS_INPUT_DIR=~/eth-statediff-service/output_dir
+CHECK_COLUMNS_INPUT_DEDUP_DIR=~/eth-statediff-service/dedup_dir
+CHECK_COLUMNS_OUTPUT_DIR=./check-columns
+
+# Used by the script to import data (timescaledb-import.sh)
+IMPORT_LOG=./tsdb-import.log
+IMPORT_INPUT_DIR=~/eth-statediff-service/output_dir
+IMPORT_INPUT_DEDUP_DIR=~/eth-statediff-service/dedup_dir
+TIMESCALEDB_WORKERS=8
+
+DATABASE_USER=vdbm
+DATABASE_HOSTNAME=localhost
+DATABASE_PORT=8077
+DATABASE_NAME=vulcanize_testing
+DATABASE_PASSWORD=password

scripts/check-columns.sh

@@ -0,0 +1,58 @@
+#!/bin/bash
+
+# Requires:
+# CHECK_COLUMNS_LOG
+# CHECK_COLUMNS_INPUT_DIR
+# CHECK_COLUMNS_INPUT_DEDUP_DIR
+# CHECK_COLUMNS_OUTPUT_DIR
+
+# env file arg
+ENV=$1
+echo "Using env file: ${ENV}"
+
+# read env file
+export $(grep -v '^#' ${ENV} | xargs)
+
+# redirect stdout/stderr to a file
+exec >"${CHECK_COLUMNS_LOG}" 2>&1
+
+# create output dir if not exists
+mkdir -p "${CHECK_COLUMNS_OUTPUT_DIR}"
+
+start_timestamp=$(date +%s)
+
+declare -A expected_columns
+expected_columns=(
+  ["public.nodes"]="5"
+  ["public.blocks"]="3"
+  # ["eth.access_list_elements"]="?" # skipping as values include ','
+  ["eth.log_cids"]="12"
+  ["eth.state_accounts"]="7"
+  ["eth.storage_cids"]="9"
+  ["eth.uncle_cids"]="7"
+  ["eth.header_cids"]="16"
+  ["eth.receipt_cids"]="10"
+  ["eth.state_cids"]="8"
+  ["eth.transaction_cids"]="11"
+)
+
+for table_name in "${!expected_columns[@]}";
+do
+  if [ "${table_name}" = "public.blocks" ];
+  then
+    command="$(dirname "$0")/find-bad-rows.sh -i ${CHECK_COLUMNS_INPUT_DEDUP_DIR}/deduped-${table_name}.csv -c ${expected_columns[${table_name}]} -d true -o ${CHECK_COLUMNS_OUTPUT_DIR}/${table_name}.txt"
+  else
+    command="$(dirname "$0")/find-bad-rows.sh -i ${CHECK_COLUMNS_INPUT_DIR}/${table_name}.csv -c ${expected_columns[${table_name}]} -d true -o ${CHECK_COLUMNS_OUTPUT_DIR}/${table_name}.txt"
+  fi
+
+  echo "${table_name}"
+  echo Start: "$(date)"
+  eval "${command}"
+  echo End: "$(date)"
+  echo Total bad rows: $(wc -l ${CHECK_COLUMNS_OUTPUT_DIR}/${table_name}.txt)
+  echo
+done
+
+difference=$(($(date +%s)-start_timestamp))
+echo Time taken: $((difference/86400)):$(date -d@${difference} -u +%H:%M:%S)
+echo

scripts/count-lines.sh

@@ -0,0 +1,46 @@
+#!/bin/bash
+
+# Requires:
+# COUNT_LINES_LOG
+# COUNT_LINES_INPUT_DIR
+# COUNT_LINES_OUTPUT_FILE
+
+# env file arg
+ENV=$1
+echo "Using env file: ${ENV}"
+
+# read env file
+export $(grep -v '^#' ${ENV} | xargs)
+
+# redirect stdout/stderr to a file
+exec >"${COUNT_LINES_LOG}" 2>&1
+
+start_timestamp=$(date +%s)
+
+table_names=(
+  "public.nodes"
+  "public.blocks"
+  "eth.access_list_elements"
+  "eth.log_cids"
+  "eth.state_accounts"
+  "eth.storage_cids"
+  "eth.uncle_cids"
+  "eth.header_cids"
+  "eth.receipt_cids"
+  "eth.state_cids"
+  "eth.transaction_cids"
+)
+
+echo "Row counts:" > "${COUNT_LINES_OUTPUT_FILE}"
+
+for table_name in "${table_names[@]}";
+do
+  echo "${table_name}";
+  echo Start: "$(date)"
+  wc -l "${COUNT_LINES_INPUT_DIR}"/"${table_name}.csv" >> "${COUNT_LINES_OUTPUT_FILE}"
+  echo End: "$(date)"
+  echo
+done
+
+difference=$(($(date +%s)-start_timestamp))
+echo Time taken: $((difference/86400)):$(date -d@${difference} -u +%H:%M:%S)

scripts/dedup.sh

@@ -0,0 +1,35 @@
+#!/bin/bash
+
+# Requires:
+# DEDUP_LOG
+# DEDUP_INPUT_DIR
+# DEDUP_OUTPUT_DIR
+# DEDUP_SORT_DIR
+
+# env file arg
+ENV=$1
+echo "Using env file: ${ENV}"
+
+# read env file
+export $(grep -v '^#' ${ENV} | xargs)
+
+# redirect stdout/stderr to a file
+exec >"${DEDUP_LOG}" 2>&1
+
+# create output dir if not exists
+mkdir -p "${DEDUP_OUTPUT_DIR}"
+
+start_timestamp=$(date +%s)
+
+echo "public.blocks"
+echo Start: "$(date)"
+sort -T "${DEDUP_SORT_DIR}" -u "${DEDUP_INPUT_DIR}"/public.blocks.csv -o "${DEDUP_OUTPUT_DIR}"/deduped-public.blocks.csv
+echo End: "$(date)"
+echo Total deduped rows: $(wc -l ${DEDUP_OUTPUT_DIR}/deduped-public.blocks.csv)
+echo
+
+difference=$(($(date +%s)-start_timestamp))
+echo Time taken: $((difference/86400)):$(date -d@${difference} -u +%H:%M:%S)
+
+# NOTE: This script currently only dedups public.blocks output file.
+# If the output contains blocks that were statediffed more than once, output files for other tables will have to be deduped as well.

scripts/find-bad-rows.sh

@@ -0,0 +1,43 @@
+#!/bin/bash
+
+# flags
+# -i <input-file>:        Input data file path
+# -c <expected-columns>:  Expected number of columns in each row of the input file
+# -o [output-file]:       Output destination file path (default: STDOUT)
+# -d [include-data]:      Whether to include the data row in output (true | false) (default: false)
+
+# eg: ./scripts/find-bad-rows.sh -i eth.state_cids.csv -c 8 -o res.txt -d true
+# output: 1 9 1500000,xxxxxxxx,0x83952d392f9b0059eea94b10d1a095eefb1943ea91595a16c6698757127d4e1c,,
+#         baglacgzasvqcntdahkxhufdnkm7a22s2eetj6mx6nzkarwxtkvy4x3bubdgq,\x0f,0,f,/blocks/,
+#         DMQJKYBGZRQDVLT2CRWVGPQNNJNCCJU7GL7G4VAI3LZVK4OL5Q2ARTI
+
+while getopts i:c:o:d: OPTION
+do
+  case "${OPTION}" in
+    i) inputFile=${OPTARG};;
+    c) expectedColumns=${OPTARG};;
+    o) outputFile=${OPTARG};;
+    d) data=${OPTARG};;
+  esac
+done
+
+timestamp=$(date +%s)
+
+# if data requested, dump row number, number of columns and the row
+if [ "${data}" = true ] ; then
+  if [ -z "${outputFile}" ]; then
+    awk -F"," "NF!=${expectedColumns} {print NR, NF, \$0}" < ${inputFile}
+  else
+    awk -F"," "NF!=${expectedColumns} {print NR, NF, \$0}" < ${inputFile} > ${outputFile}
+  fi
+# else, dump only row number, number of columns
+else
+  if [ -z "${outputFile}" ]; then
+    awk -F"," "NF!=${expectedColumns} {print NR, NF}" < ${inputFile}
+  else
+    awk -F"," "NF!=${expectedColumns} {print NR, NF}" < ${inputFile} > ${outputFile}
+  fi
+fi
+
+difference=$(($(date +%s)-timestamp))
+echo Time taken: $(date -d@${difference} -u +%H:%M:%S)

scripts/request-range.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+
+set -eu
+
+FROM=$1
+TO=$2
+URL=127.0.0.1:8545
+
+DATA='{
+    "jsonrpc": "2.0",
+      "method": "statediff_writeStateDiffsInRange",
+      "params": ['"$FROM"', '"$TO"', {
+          "includeBlock": true,
+          "includeReceipts": true,
+          "includeTD": true,
+          "includeCode": true
+        }
+      ],
+      "id": 1
+}'
+
+exec curl -s $URL -X POST -H 'Content-Type: application/json' --data "$DATA"

scripts/timescaledb-import.sh

@@ -0,0 +1,75 @@
+#!/bin/bash
+
+# Requires:
+# IMPORT_LOG
+# IMPORT_INPUT_DIR
+# IMPORT_INPUT_DEDUP_DIR
+# TIMESCALEDB_WORKERS
+# DATABASE_USER
+# DATABASE_HOSTNAME
+# DATABASE_PORT
+# DATABASE_NAME
+# DATABASE_PASSWORD
+
+DEFAULT_TIMESCALEDB_WORKERS=8
+
+# env file arg
+ENV=$1
+echo "Using env file: ${ENV}"
+
+# read env file
+export $(grep -v '^#' ${ENV} | xargs)
+
+if [ "$TIMESCALEDB_WORKERS" = "" ]; then
+	TIMESCALEDB_WORKERS=$DEFAULT_TIMESCALEDB_WORKERS
+fi
+
+# redirect stdout/stderr to a file
+exec >"${IMPORT_LOG}" 2>&1
+
+start_timestamp=$(date +%s)
+
+declare -a tables
+# schema-table-copyOptions
+tables=(
+  "public-nodes"
+  "public-blocks"
+  "eth-access_list_elements"
+  "eth-log_cids-FORCE NOT NULL topic0, topic1, topic2, topic3 CSV"
+  "eth-state_accounts"
+  "eth-storage_cids-FORCE NOT NULL storage_leaf_key CSV"
+  "eth-uncle_cids"
+  "eth-header_cids"
+  "eth-receipt_cids-FORCE NOT NULL post_state, contract, contract_hash CSV"
+  "eth-state_cids-FORCE NOT NULL state_leaf_key CSV"
+  "eth-transaction_cids-FORCE NOT NULL dst CSV"
+)
+
+for elem in "${tables[@]}";
+do
+	IFS='-' read -a arr <<< "${elem}"
+
+	if [ "${arr[0]}.${arr[1]}" = "public.blocks" ];
+	then
+		copy_command="timescaledb-parallel-copy --connection \"host=${DATABASE_HOSTNAME} port=${DATABASE_PORT} user=${DATABASE_USER} password=${DATABASE_PASSWORD} sslmode=disable\" --db-name ${DATABASE_NAME} --schema ${arr[0]} --table ${arr[1]} --file ${IMPORT_INPUT_DEDUP_DIR}/deduped-${arr[0]}.${arr[1]}.csv --workers ${TIMESCALEDB_WORKERS} --reporting-period 300s"
+	else
+		copy_command="timescaledb-parallel-copy --connection \"host=${DATABASE_HOSTNAME} port=${DATABASE_PORT} user=${DATABASE_USER} password=${DATABASE_PASSWORD} sslmode=disable\" --db-name ${DATABASE_NAME} --schema ${arr[0]} --table ${arr[1]} --file ${IMPORT_INPUT_DIR}/${arr[0]}.${arr[1]}.csv --workers ${TIMESCALEDB_WORKERS} --reporting-period 300s"
+	fi
+
+	if [ "${arr[2]}" != "" ];
+	then
+		copy_with_options="${copy_command} --copy-options \"${arr[2]}\""
+	else
+		copy_with_options=${copy_command}
+	fi
+
+	echo "${arr[0]}.${arr[1]}"
+	echo Start: "$(date)"
+	eval "${copy_with_options}"
+	echo End: "$(date)"
+	echo
+done
+
+difference=$(($(date +%s)-start_timestamp))
+echo Time taken: $((difference/86400)):$(date -d@${difference} -u +%H:%M:%S)
+echo

startup_script.sh

@@ -17,4 +17,4 @@ mkdir -p /app/geth-rw && \
 sudo mount -t overlay overlay -o lowerdir=/app/geth-ro,upperdir=/tmp/overlay/upper,workdir=/tmp/overlay/work /app/geth-rw && \
 
 echo "Running the statediff service" && \
-exec sudo ./eth-statediff-service "$VDB_COMMAND" --config=config.toml
+exec sudo ./eth-statediff-service "$VDB_COMMAND" --config=/config/config.toml

test/ci-chain.json

@@ -0,0 +1,16 @@
+{
+  "chainId": 41337,
+  "homesteadBlock": 0,
+  "eip150Block": 0,
+  "eip150Hash": "0x0000000000000000000000000000000000000000000000000000000000000000",
+  "eip155Block": 0,
+  "eip158Block": 0,
+  "byzantiumBlock": 0,
+  "constantinopleBlock": 0,
+  "petersburgBlock": 0,
+  "istanbulBlock": 0,
+  "clique": {
+    "period": 5,
+    "epoch": 30000
+  }
+}

test/ci-config.toml

@@ -0,0 +1,36 @@
+[leveldb]
+    mode = "local"
+    url = "http://127.0.0.1:8082/"
+
+[server]
+    ipcPath = ".ipc"
+    httpPath = "0.0.0.0:8545"
+
+[statediff]
+    serviceWorkers = 1
+    workerQueueSize = 1024
+    trieWorkers = 4
+
+[log]
+    level = "debug"
+
+[database]
+    name            = "cerc_testing"
+    hostname        = "localhost"
+    port            = 8077
+    user            = "vdbm"
+    password        = "password"
+    type            = "postgres"
+    driver          = "sqlx"
+
+[cache]
+    database = 1024
+    trie = 1024
+
+[ethereum]
+    chainConfig = "test/ci-chain.json"
+    nodeID = ""
+    clientName = "eth-statediff-service"
+    genesisBlock = "0x37cbb63c7150a7b60f2878433963ed8ba7e5f82fb2683ec7a945c974e1cf4e05"
+    networkID = 1
+    chainID = 41337

test/compose.yml

@@ -0,0 +1,23 @@
+services:
+  migrations:
+    restart: on-failure
+    depends_on:
+      - ipld-eth-db
+    image: git.vdb.to/cerc-io/ipld-eth-db/ipld-eth-db:v5.0.5-alpha
+    environment:
+      DATABASE_USER: "vdbm"
+      DATABASE_NAME: "cerc_testing"
+      DATABASE_PASSWORD: "password"
+      DATABASE_HOSTNAME: "ipld-eth-db"
+      DATABASE_PORT: 5432
+
+  ipld-eth-db:
+    image: timescale/timescaledb:latest-pg14
+    restart: always
+    command: ["postgres", "-c", "log_statement=all"]
+    environment:
+      POSTGRES_USER: "vdbm"
+      POSTGRES_DB: "cerc_testing"
+      POSTGRES_PASSWORD: "password"
+    ports:
+      - 127.0.0.1:8077:5432